Biological Neural Systems-presentation
This document was uploaded by user and they confirmed that they have the permission to share it. If you are author or own the copyright of this book, please report to us by using this DMCA report form. Report DMCA
Overview
Download & View Biological Neural Systems-presentation as PDF for free.
More details
- Words: 3,288
- Pages: 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Email: [email protected] URL: http://www.geocities.com/vshrao
Fellow of National Academy of Sciences, India Fellow of Institution of Electronics & Telecommunication Engineers, India Fellow of Forum D’Analystes Professor of Mathematics Jawaharlal Nehru Technological University Hyderabad - 500 072, India
V. Sree Hari Rao
Biological Neural Systems to Artificial Neural Systems – An Evolution
Page 1 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
evolves to become better adapted.
learns from the environment with minimal human intervention,
rapidly processes large amounts of data in a massively parallel fashion,
robustly handles data with large amounts of noise,
functions with high degrees of autonomy,
continually acts, mentally and externally, and by acting reaches its objectives
learns during its existence
Intelligent System:
to develop Intelligent Systems
FUNDAMENTAL OBJECTIVE OF COMPUTING IS
Page 2 / 30
SWARM BOTS
ANTS
Email: [email protected]; URL: http://www.geocities.com/vshrao
Page 3 / 30
ROBOTIC MOVEMENTS
INSECTS
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
AIR CRAFTS
BIRDS
Nature is influencing researchers in many ways. History shows that many scientific investigations were motivated by natural phenomena.
Nature’s Influence on Scientific Investigations
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
SPIDER WEB
HORSE CART
HORSE
Page 4 / 30
RESISTANCE MATERIALS
SHIP
FISH
Nature’s Influence on Scientific Investigations (Contd…)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 5 / 30
The development and progress of computer science, engineering and technology has greatly contributed to the study of biological systems and sciences to gain a better understanding of biological processes and functions through the modeling and simulation of natural systems.
It is a multi disciplinary field strongly based on biology, mathematics, computer science, informatics, cognitive science, control theory and robotics.
producing informatics tools with enhanced robustness, scalability, flexibility, and which can interface more effectively with humans.
tackling complex problems using computational methods modeled after design principles encountered in nature.
focuses on set of techniques inspired by biological sciences. Biological organisms often exhibit properties that would be desirable in computer systems. Some features of bio-inspired computing include:
Bio-inspired Computing:
Email: [email protected]; URL: http://www.geocities.com/vshrao
Page 6 / 30
DNA COMPUTING BIODEGRADABILITY PREDICTION EXCITABLE MEDIA
GENETIC ALGORITHMS CELLULAR AUTOMATA EMERGENT SYSTEMS NEURAL NETWORKS ARTIFICIAL LIFE ARTIFICIAL IMMUNE SYSTEMS LINDENMAYER SYSTEMS MEMBRANE COMPUTERS
Bio-Inspired Systems
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
EVOLUTION LIFE INSECT COLONIES, ANTS, BEES etc THE BRAIN LIFE IMMUNE SYSTEM PLANT STRUCTURES INTRAMEMBRANE MOLECULAR PROCESSES IN LIVING CELL DNA and MOLECULAR BIOLOGY BIODEGRADATION FOREST FIRES
Biological Systems / Process
The Present day researcher generates new ideas by taking advantage of the examples provided by the nature.
Bio-Inspired Techniques:
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Dendrites are the branches that are coming out of the neuron. These act as the antennae of the neuron.
The Axon is specialized for transferring information over a certain distance in the nervous hillock.
The typical cell body of a neuron measures about 20 micrometers in diameter.
Page 7 / 30
The neuron consists of CELL BODY / SOMA, the AXON, DENDRITES and the NEURONAL MEMBRANE
Cells of nervous system or nerve cells are commonly called neurons. The purpose of the neuron is to transmit messages through an electrochemical process throughout the nervous system. These cells come in different shapes and sizes.
The Neuron:
Structure of the Biological Neuron
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
The Neuron
Page 8 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Connections between two Biological Neurons
Page 9 / 30
Thus, the routine processes are performed subconsciously while the conscious “focus of attention” or ‘short – term working memory’ attends to the important aspects.
“As a task to be learned is practiced, its performance becomes more and more automatic; as this occurs, it fades from consciousness, the number of brain regions involved in the task becomes smaller.” Edelman & Tononi
The brain is a complex multi-processing system. To simplify thinking process, regular activities are routinized so that they require less brain activity and we do not have to attend to them consciously:
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 10 / 30
The structure of the human brain differs from that of other animals in several important ways. These differences allow for many abilities over and above those of other animals, such as advanced cognitive skills. Much of human brain structure is similar to that of other mammals. The human brain also has a massive number of synaptic connections allowing for a great deal of PARALLEL PROCESSING
The Biological Brain
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
A single neuron can be connected to many other neurons and the total number of neurons and connections in a network can be extremely large.
Biological Neural Nets are made up of real biological neurons that are connected or functionally – related in the peripheral nervous system or the central nervous system. In the field of neuroscience, they are often identified as groups of neurons that perform a specific physiological function in laboratory analysis.
Biological Neural Nets:
Page 11 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 12 / 30
The part of Soma that does concern itself with the signal is Axon hillock. If the aggregate input is greater than the axon hillock’s threshold value, then the neuron fires, and an output signal is transmitted down the axon.
The aggregate input is then passed to the soma or cell body. The soma and enclosed nucleus don’t play a significant role in the processing of incoming and outgoing data. Their primary function is to perform the continuous maintenance required to keep the neuron functional.
Spatial summation occurs when several weak signals are converted in to a single large one, while temporal summation converts a rapid series of weak pulses from one source in to one large signal.
The strengths of all received charges are added together through a process of spatial and temporal summation.
A neuron’s dendritic tree is connected to a thousand neighboring neurons. When one of those neurons fire, a positive or negative charge is received by one of the dendrites.
The brain is a collection of about 10 billion interconnected neurons. Each neuron is a cell that uses biochemical reactions to receive, process and transmit information.
Functioning of the Biological Neuron
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 13 / 30
Each terminal button is connected to the other neurons across a small gap called a Synapse. The physical and neuro-chemical characteristics of each synapse determine the strength and polarity of the new input signal.
The strength of the output is constant; regard less of whether the input was just above the threshold or a hundred times as great. The output strength is unaffected by the many divisions in the axon; it reaches each terminal button with the same intensity it had at the axon hillock.
Functioning of the Biological Neuron (Contd..)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
A Schematic diagram of a biological neuron
Page 14 / 30
The computer uses electricity. Computer memory grows by adding computer chips.
The brain uses chemicals to transmit information. Memories in the brain grow by stronger synaptic connections. It is much easier and faster for the brain to learn new things. The human brain has weighed in at about 3 pounds for about the last 100,000 years.
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
‘There is more we do not know about the brain, than what we know’
Page 15 / 30
The computer can do many complex tasks at the same time that are difficult for the brain. Computers have evolved much faster than the human brain. The technological developments have made computers faster, smaller and more powerful. There are no new or used parts for the brain. Some It is easy to update computer with new parts. work is being done with transplantation of nerve cells for certain neurological disorders such as Parkinson’s disease. There are diseases that affect the brain. Computer can get a ‘VIRUS’. The brain is always changing and being modified. The computer only changes when a new hardware/software is added or some thing is saved in There is no ‘OFF’ for the brain. Even when an the memory. There is an ‘OFF’ for a computer when animal is sleeping, its brain is still active and the power is turned off. working. The brain is better at interpreting the outside The computer is faster at doing logical things and world and coming up with new ideas. computations.
COMPUTER
BRAIN
The Brain and the Computer
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 16 / 30
are similar to the biological neural networks in the sense that functions are performed collectively and in parallel by the units.
are adaptive systems that changes their structure based on external or internal information that flows through the network.
use a mathematical or computational model for information processing based on connectionist approach to computation.
are made up of interconnecting artificial neurons designed to mimic some properties of biological neural networks.
are inspired by neuro - scientific studies of the structure and function of human brain
Artificial Neural Networks (ANNs)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
composed of many neurons that co-operate to perform the desired function.
Outputs
Inputs NN
Outputs
Transforms inputs in to outputs to the best of its ability.
Inputs
essentially a function approximator.
an extremely simplified model of the brain.
Thus ANN is
Artificial Neural Networks (Contd…)
Page 17 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 18 / 30
Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.
Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability.
Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time.
Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience.
Other Advantages
Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. A trained neural network can be thought of as an "expert" in the category of information it has been given to analyze. This expert can then be used to provide projections given new situations of interest and answer "what if" questions.
Why use Neural Networks?
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 19 / 30
is the study of system behavior. The behavior refers to external input / output characteristics and internal state changes. The behavior can be described in terms of qualitative or quantitative relationships among variables defined for the system. A system can be imitated or simulated by something which we call a MODEL. A system may be represented by a block diagram. In this representation, the system is treated as a ‘black box’ whose internal behavior is opaque, and its behavior is described by external input / output relationships.
System Theory
The assumptions of a closed system under certain restrictions is a means to simplify the analysis of system behavior.
An open system is a system that is influenced by its environment, where as a closed system is one isolated from its environment
Function of the system depends not only on the functions of the constituents but also on how they connect to one another.
System is the connected units or parts that form a whole and operate together.
Basic nomenclature and facts:
Mathematical Modeling
Simulation
Mathematical Model
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
One can divide modeling strategies in to theory- driven, data – driven, and mixed.
An Important Question is how to construct a model?
Page 20 / 30
An experiment is performed to gather the relevant data for estimating model parameters or evaluating the model. A model needs to be refined or replaced if it does not provide sufficiently accurate results.
Fig. An overview of the problem of mathematical modeling
Real Physical System
Abstraction
In scientific investigations, a model is constructed to explain a hypothesis or to simulate a practical system (as shown in the fig. below)
Mathematical Modeling in General
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Output variables (endogenous variables) whose behavior is modeled.
Page 21 / 30
Input variables (exogenous variables) which affect the system but whose behavior is not modeled.
Variables which can be neglected
Modeling involves identification of:
Test and analyze the model.
Develop model equations and estimate model parameters from relevant data.
Describe each element mathematically, based on physical laws.
Define variables of interest.
Postulate the structure of the model, for example, in terms of block diagram.
Define the boundaries of the model.
Specify the purpose of the model.
Define the problem for which a model is developed.
Steps involved in Mathematical Modeling
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
a baseline control
a mathematical model
a postprocessor
a preprocessor
A neural network can be applied to mathematical modeling as
Page 22 / 30
The modeling capability of the neural network can be ascribed to its ability to learn the mathematical function underlying the system operation.
The neural network learns to map an input into a desired output by self-adaptation.
Given a physical system, a neural network can model it on the basis of a set of examples encoding the input / output behavior of the system.
Neural Networks and Mathematical Modeling
Modeling Techniques
Post processor Neural Network
The integration of neural networks with other modeling techniques
Preprocessor Neural Network
Mathematical Model
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 23 / 30
A common practice is to select a tentative set of variables and refine the set successively.
A difficult part of building a model is to determine which variables should be included in the model. Introducing irrelevant variables and missing relevant ones are both deleterious to the model.
Data
Integration of neural networks with other modeling techniques
Neural Networks Single-layer networks Multilayer networks Static networks Temporal networks Deterministic networks (e.g., back propagation network) Stochastic networks (e.g., the Boltzmann machine) Discrete networks Continuous networks
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Fig. A mapping neural network.
Input layer
Hidden layer
Output layer
………
Y
….…….
Y = f ( X 1,.... Xn).
Page 24 / 30
The basis of using neural networks as mathematical models is “MAPPING”.
Discrete models Continuous models
Stochastic models
Mathematical Models Linear models Nonlinear models Static models Dynamic models Deterministic models
Correspondence between neural networks and mathematical models
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Pattern recognition Diagnosis of hepatitis Undersea mine detection Texture analysis 3-D object recognition Hand-written word recognition Estimation of the rate of spread of an epidemic Facial recognition
Some typical examples also include
Classification Noise Reduction Sales forecasting Industrial process control Customer research Data validation Risk management Target marketing
Neural nets have broad applicability to real world problems. Some areas include
Applications of ANNs:
Page 25 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 26 / 30
instability to explain any results that they obtain. Networks function as "black boxes” whose rules of operation are completely unknown.
the operational problem encountered when attempting to simulate the parallelism of neural networks. Since the majority of neural networks are simulated on sequential machines, giving rise to a very rapid increase in processing time requirements as size of the problem expands.
Also there are some more practical problems like:
The mathematical theories used to guarantee the performance of an applied neural network are still under development. The solution for the time being may be to train and test these intelligent systems much as we do for humans.
Neural network programs sometimes become unstable when applied to larger problems. The defense, nuclear and space industries are concerned about the issue of testing and verification.
The major issues of concern today are the scalability problem, testing, verification, and integration of neural network systems into the modern environment.
Are there any limits to Neural Networks?
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 27 / 30
This "programming" would require feedback from the user in order to be effective but simple and "passive" sensors (e.g. fingertip sensors, gloves, or wristbands to sense pulse, blood pressure, skin ionization, and so on), could provide effective feedback into a neural control system. This could be achieved, for example, with sensors that would detect pulse, blood pressure, skin ionization, and other variables which the system could learn to correlate with a person's response state.
Neural Networks will fascinate user-specific systems for education, information processing, and entertainment. "Alternative realities", produced by comprehensive environments, are attractive in terms of their potential for systems control, education, and entertainment. This is not just a far-out research trend, but is something which is becoming an increasing part of our daily existence, as witnessed by the growing interest in comprehensive "entertainment centers" in each home.
Prediction 1:
Because gazing into the future is somewhat like gazing into a crystal ball, so it is better to quote some "predictions". Each prediction rests on some sort of evidence or established trend which, with extrapolation, clearly takes us into a new realm.
The Future
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 28 / 30
Neural networks will allow us to explore new realms of human capability realms previously available only with extensive training and personal discipline. So a specific state of consciously induced neuro-physiologically observable awareness is necessary in order to facilitate a man machine system interface.
Prediction 3:
Neural networks, integrated with other artificial intelligence technologies, methods for direct culture of nervous tissue, and other exotic technologies such as genetic engineering, will allow us to develop radical and exotic life-forms whether man, machine, or hybrid.
Prediction 2:
The Future (Contd...)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Von Neumann with the first computer
Page 29 / 30
ALL UNSTABLE PROCESSES WE CAN CONTROL
ALL STABLE PROCESSES WE CAN PREDICT.
John von Neumann
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 30 / 30
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Email: [email protected] URL: http://www.geocities.com/vshrao
Fellow of National Academy of Sciences, India Fellow of Institution of Electronics & Telecommunication Engineers, India Fellow of Forum D’Analystes Professor of Mathematics Jawaharlal Nehru Technological University Hyderabad - 500 072, India
V. Sree Hari Rao
Biological Neural Systems to Artificial Neural Systems – An Evolution
Page 1 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
evolves to become better adapted.
learns from the environment with minimal human intervention,
rapidly processes large amounts of data in a massively parallel fashion,
robustly handles data with large amounts of noise,
functions with high degrees of autonomy,
continually acts, mentally and externally, and by acting reaches its objectives
learns during its existence
Intelligent System:
to develop Intelligent Systems
FUNDAMENTAL OBJECTIVE OF COMPUTING IS
Page 2 / 30
SWARM BOTS
ANTS
Email: [email protected]; URL: http://www.geocities.com/vshrao
Page 3 / 30
ROBOTIC MOVEMENTS
INSECTS
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
AIR CRAFTS
BIRDS
Nature is influencing researchers in many ways. History shows that many scientific investigations were motivated by natural phenomena.
Nature’s Influence on Scientific Investigations
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
SPIDER WEB
HORSE CART
HORSE
Page 4 / 30
RESISTANCE MATERIALS
SHIP
FISH
Nature’s Influence on Scientific Investigations (Contd…)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 5 / 30
The development and progress of computer science, engineering and technology has greatly contributed to the study of biological systems and sciences to gain a better understanding of biological processes and functions through the modeling and simulation of natural systems.
It is a multi disciplinary field strongly based on biology, mathematics, computer science, informatics, cognitive science, control theory and robotics.
producing informatics tools with enhanced robustness, scalability, flexibility, and which can interface more effectively with humans.
tackling complex problems using computational methods modeled after design principles encountered in nature.
focuses on set of techniques inspired by biological sciences. Biological organisms often exhibit properties that would be desirable in computer systems. Some features of bio-inspired computing include:
Bio-inspired Computing:
Email: [email protected]; URL: http://www.geocities.com/vshrao
Page 6 / 30
DNA COMPUTING BIODEGRADABILITY PREDICTION EXCITABLE MEDIA
GENETIC ALGORITHMS CELLULAR AUTOMATA EMERGENT SYSTEMS NEURAL NETWORKS ARTIFICIAL LIFE ARTIFICIAL IMMUNE SYSTEMS LINDENMAYER SYSTEMS MEMBRANE COMPUTERS
Bio-Inspired Systems
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
EVOLUTION LIFE INSECT COLONIES, ANTS, BEES etc THE BRAIN LIFE IMMUNE SYSTEM PLANT STRUCTURES INTRAMEMBRANE MOLECULAR PROCESSES IN LIVING CELL DNA and MOLECULAR BIOLOGY BIODEGRADATION FOREST FIRES
Biological Systems / Process
The Present day researcher generates new ideas by taking advantage of the examples provided by the nature.
Bio-Inspired Techniques:
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Dendrites are the branches that are coming out of the neuron. These act as the antennae of the neuron.
The Axon is specialized for transferring information over a certain distance in the nervous hillock.
The typical cell body of a neuron measures about 20 micrometers in diameter.
Page 7 / 30
The neuron consists of CELL BODY / SOMA, the AXON, DENDRITES and the NEURONAL MEMBRANE
Cells of nervous system or nerve cells are commonly called neurons. The purpose of the neuron is to transmit messages through an electrochemical process throughout the nervous system. These cells come in different shapes and sizes.
The Neuron:
Structure of the Biological Neuron
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
The Neuron
Page 8 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Connections between two Biological Neurons
Page 9 / 30
Thus, the routine processes are performed subconsciously while the conscious “focus of attention” or ‘short – term working memory’ attends to the important aspects.
“As a task to be learned is practiced, its performance becomes more and more automatic; as this occurs, it fades from consciousness, the number of brain regions involved in the task becomes smaller.” Edelman & Tononi
The brain is a complex multi-processing system. To simplify thinking process, regular activities are routinized so that they require less brain activity and we do not have to attend to them consciously:
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 10 / 30
The structure of the human brain differs from that of other animals in several important ways. These differences allow for many abilities over and above those of other animals, such as advanced cognitive skills. Much of human brain structure is similar to that of other mammals. The human brain also has a massive number of synaptic connections allowing for a great deal of PARALLEL PROCESSING
The Biological Brain
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
A single neuron can be connected to many other neurons and the total number of neurons and connections in a network can be extremely large.
Biological Neural Nets are made up of real biological neurons that are connected or functionally – related in the peripheral nervous system or the central nervous system. In the field of neuroscience, they are often identified as groups of neurons that perform a specific physiological function in laboratory analysis.
Biological Neural Nets:
Page 11 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 12 / 30
The part of Soma that does concern itself with the signal is Axon hillock. If the aggregate input is greater than the axon hillock’s threshold value, then the neuron fires, and an output signal is transmitted down the axon.
The aggregate input is then passed to the soma or cell body. The soma and enclosed nucleus don’t play a significant role in the processing of incoming and outgoing data. Their primary function is to perform the continuous maintenance required to keep the neuron functional.
Spatial summation occurs when several weak signals are converted in to a single large one, while temporal summation converts a rapid series of weak pulses from one source in to one large signal.
The strengths of all received charges are added together through a process of spatial and temporal summation.
A neuron’s dendritic tree is connected to a thousand neighboring neurons. When one of those neurons fire, a positive or negative charge is received by one of the dendrites.
The brain is a collection of about 10 billion interconnected neurons. Each neuron is a cell that uses biochemical reactions to receive, process and transmit information.
Functioning of the Biological Neuron
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 13 / 30
Each terminal button is connected to the other neurons across a small gap called a Synapse. The physical and neuro-chemical characteristics of each synapse determine the strength and polarity of the new input signal.
The strength of the output is constant; regard less of whether the input was just above the threshold or a hundred times as great. The output strength is unaffected by the many divisions in the axon; it reaches each terminal button with the same intensity it had at the axon hillock.
Functioning of the Biological Neuron (Contd..)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
A Schematic diagram of a biological neuron
Page 14 / 30
The computer uses electricity. Computer memory grows by adding computer chips.
The brain uses chemicals to transmit information. Memories in the brain grow by stronger synaptic connections. It is much easier and faster for the brain to learn new things. The human brain has weighed in at about 3 pounds for about the last 100,000 years.
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
‘There is more we do not know about the brain, than what we know’
Page 15 / 30
The computer can do many complex tasks at the same time that are difficult for the brain. Computers have evolved much faster than the human brain. The technological developments have made computers faster, smaller and more powerful. There are no new or used parts for the brain. Some It is easy to update computer with new parts. work is being done with transplantation of nerve cells for certain neurological disorders such as Parkinson’s disease. There are diseases that affect the brain. Computer can get a ‘VIRUS’. The brain is always changing and being modified. The computer only changes when a new hardware/software is added or some thing is saved in There is no ‘OFF’ for the brain. Even when an the memory. There is an ‘OFF’ for a computer when animal is sleeping, its brain is still active and the power is turned off. working. The brain is better at interpreting the outside The computer is faster at doing logical things and world and coming up with new ideas. computations.
COMPUTER
BRAIN
The Brain and the Computer
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 16 / 30
are similar to the biological neural networks in the sense that functions are performed collectively and in parallel by the units.
are adaptive systems that changes their structure based on external or internal information that flows through the network.
use a mathematical or computational model for information processing based on connectionist approach to computation.
are made up of interconnecting artificial neurons designed to mimic some properties of biological neural networks.
are inspired by neuro - scientific studies of the structure and function of human brain
Artificial Neural Networks (ANNs)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
composed of many neurons that co-operate to perform the desired function.
Outputs
Inputs NN
Outputs
Transforms inputs in to outputs to the best of its ability.
Inputs
essentially a function approximator.
an extremely simplified model of the brain.
Thus ANN is
Artificial Neural Networks (Contd…)
Page 17 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 18 / 30
Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.
Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability.
Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time.
Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience.
Other Advantages
Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. A trained neural network can be thought of as an "expert" in the category of information it has been given to analyze. This expert can then be used to provide projections given new situations of interest and answer "what if" questions.
Why use Neural Networks?
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 19 / 30
is the study of system behavior. The behavior refers to external input / output characteristics and internal state changes. The behavior can be described in terms of qualitative or quantitative relationships among variables defined for the system. A system can be imitated or simulated by something which we call a MODEL. A system may be represented by a block diagram. In this representation, the system is treated as a ‘black box’ whose internal behavior is opaque, and its behavior is described by external input / output relationships.
System Theory
The assumptions of a closed system under certain restrictions is a means to simplify the analysis of system behavior.
An open system is a system that is influenced by its environment, where as a closed system is one isolated from its environment
Function of the system depends not only on the functions of the constituents but also on how they connect to one another.
System is the connected units or parts that form a whole and operate together.
Basic nomenclature and facts:
Mathematical Modeling
Simulation
Mathematical Model
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
One can divide modeling strategies in to theory- driven, data – driven, and mixed.
An Important Question is how to construct a model?
Page 20 / 30
An experiment is performed to gather the relevant data for estimating model parameters or evaluating the model. A model needs to be refined or replaced if it does not provide sufficiently accurate results.
Fig. An overview of the problem of mathematical modeling
Real Physical System
Abstraction
In scientific investigations, a model is constructed to explain a hypothesis or to simulate a practical system (as shown in the fig. below)
Mathematical Modeling in General
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Output variables (endogenous variables) whose behavior is modeled.
Page 21 / 30
Input variables (exogenous variables) which affect the system but whose behavior is not modeled.
Variables which can be neglected
Modeling involves identification of:
Test and analyze the model.
Develop model equations and estimate model parameters from relevant data.
Describe each element mathematically, based on physical laws.
Define variables of interest.
Postulate the structure of the model, for example, in terms of block diagram.
Define the boundaries of the model.
Specify the purpose of the model.
Define the problem for which a model is developed.
Steps involved in Mathematical Modeling
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
a baseline control
a mathematical model
a postprocessor
a preprocessor
A neural network can be applied to mathematical modeling as
Page 22 / 30
The modeling capability of the neural network can be ascribed to its ability to learn the mathematical function underlying the system operation.
The neural network learns to map an input into a desired output by self-adaptation.
Given a physical system, a neural network can model it on the basis of a set of examples encoding the input / output behavior of the system.
Neural Networks and Mathematical Modeling
Modeling Techniques
Post processor Neural Network
The integration of neural networks with other modeling techniques
Preprocessor Neural Network
Mathematical Model
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 23 / 30
A common practice is to select a tentative set of variables and refine the set successively.
A difficult part of building a model is to determine which variables should be included in the model. Introducing irrelevant variables and missing relevant ones are both deleterious to the model.
Data
Integration of neural networks with other modeling techniques
Neural Networks Single-layer networks Multilayer networks Static networks Temporal networks Deterministic networks (e.g., back propagation network) Stochastic networks (e.g., the Boltzmann machine) Discrete networks Continuous networks
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Fig. A mapping neural network.
Input layer
Hidden layer
Output layer
………
Y
….…….
Y = f ( X 1,.... Xn).
Page 24 / 30
The basis of using neural networks as mathematical models is “MAPPING”.
Discrete models Continuous models
Stochastic models
Mathematical Models Linear models Nonlinear models Static models Dynamic models Deterministic models
Correspondence between neural networks and mathematical models
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Pattern recognition Diagnosis of hepatitis Undersea mine detection Texture analysis 3-D object recognition Hand-written word recognition Estimation of the rate of spread of an epidemic Facial recognition
Some typical examples also include
Classification Noise Reduction Sales forecasting Industrial process control Customer research Data validation Risk management Target marketing
Neural nets have broad applicability to real world problems. Some areas include
Applications of ANNs:
Page 25 / 30
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 26 / 30
instability to explain any results that they obtain. Networks function as "black boxes” whose rules of operation are completely unknown.
the operational problem encountered when attempting to simulate the parallelism of neural networks. Since the majority of neural networks are simulated on sequential machines, giving rise to a very rapid increase in processing time requirements as size of the problem expands.
Also there are some more practical problems like:
The mathematical theories used to guarantee the performance of an applied neural network are still under development. The solution for the time being may be to train and test these intelligent systems much as we do for humans.
Neural network programs sometimes become unstable when applied to larger problems. The defense, nuclear and space industries are concerned about the issue of testing and verification.
The major issues of concern today are the scalability problem, testing, verification, and integration of neural network systems into the modern environment.
Are there any limits to Neural Networks?
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 27 / 30
This "programming" would require feedback from the user in order to be effective but simple and "passive" sensors (e.g. fingertip sensors, gloves, or wristbands to sense pulse, blood pressure, skin ionization, and so on), could provide effective feedback into a neural control system. This could be achieved, for example, with sensors that would detect pulse, blood pressure, skin ionization, and other variables which the system could learn to correlate with a person's response state.
Neural Networks will fascinate user-specific systems for education, information processing, and entertainment. "Alternative realities", produced by comprehensive environments, are attractive in terms of their potential for systems control, education, and entertainment. This is not just a far-out research trend, but is something which is becoming an increasing part of our daily existence, as witnessed by the growing interest in comprehensive "entertainment centers" in each home.
Prediction 1:
Because gazing into the future is somewhat like gazing into a crystal ball, so it is better to quote some "predictions". Each prediction rests on some sort of evidence or established trend which, with extrapolation, clearly takes us into a new realm.
The Future
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 28 / 30
Neural networks will allow us to explore new realms of human capability realms previously available only with extensive training and personal discipline. So a specific state of consciously induced neuro-physiologically observable awareness is necessary in order to facilitate a man machine system interface.
Prediction 3:
Neural networks, integrated with other artificial intelligence technologies, methods for direct culture of nervous tissue, and other exotic technologies such as genetic engineering, will allow us to develop radical and exotic life-forms whether man, machine, or hybrid.
Prediction 2:
The Future (Contd...)
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Von Neumann with the first computer
Page 29 / 30
ALL UNSTABLE PROCESSES WE CAN CONTROL
ALL STABLE PROCESSES WE CAN PREDICT.
John von Neumann
Email: [email protected]; URL: http://www.geocities.com/vshrao
V. Sree Hari Rao, Jawaharlal Nehru Technological University, Hyderabad – 500 072
Page 30 / 30
Related Documents
Biological Neural Systems-presentation
November 2019 3
Neural
December 2019 37
Biological
June 2020 20
Biological Magnification
November 2019 22
Biological Programming
August 2019 50