1 / 40

Biological Inspiration - Brain versus Computer

Biological Inspiration - Brain versus Computer. Dr. John MacIntyre Ext 3778 Email john.macintyre@sunderland.ac.uk. Pattern Recognition. Brain and Machine. The Brain Pattern Recognition Association Complexity Noise Tolerance. The Machine Calculation Precision Logic.

olivia-hyde
Download Presentation

Biological Inspiration - Brain versus Computer

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Biological Inspiration -Brain versus Computer Dr. John MacIntyre Ext 3778 Email john.macintyre@sunderland.ac.uk

  2. Pattern Recognition

  3. Brain and Machine • The Brain • Pattern Recognition • Association • Complexity • Noise Tolerance • The Machine • Calculation • Precision • Logic

  4. The contrast in architecture • The Von Neumann architecture uses a single processing unit; • Tens of millions of operations per second • Absolute arithmetic precision • The brain uses many slow unreliable processors acting in parallel

  5. Features of the Brain • Ten billion neurons • Average several thousand connections • Hundreds of operations per second • Reliability low • Die off frequently (never replaced) • Compensates for problems by massive parallelism

  6. The biological inspiration • The brain has been extensively studied by scientists. • Vast complexity prevents all but rudimentary understanding. • Even the behavior of an individual neuron is extremely complex

  7. The biological inspiration • Single “percepts” distributed among many neurons • Localized parts of the brain are responsible for certain well-defined functions (e.g.. vision, motion). • Which features are integral to the brain's performance? • Which are incidentals imposed by the fact of biology?

  8. The Structure of Neurones

  9. The Structure of Neurones A neurone has a cell body, a branching input structure (the dendrIte) and a branching output structure (th axOn) • Axons connect to dendrites via synapses. • Electro-chemical signals are propagated from the dendritic input, through the cell body, and down the axon to other neurons

  10. The Structure of Neurones • A neurone only fires if its input signal exceeds a certain amount (the threshold) in a short time period. • Synapses vary in strength • Good connections allowing a large signal • Slight connections allow only a weak signal. • Synapses can be either excitatory or inhibitory.

  11. +1 ao wj0 wj1 a1 wj2 a2 Sj f (Sj) Xj wjn an A Classic Artifical Neuron

  12. Hebbian Learning • Two neurons represent two concepts • Synaptic strength between them indicates strength of association of concepts; • Hebbian learning • connections are strengthened whenever two concepts occur together; • Pavlovian Conditioning • An animal is trained to associate two events • i.e. dinner is served after gong rings

  13. History of Neural Networks 1943 - McCulloch and Pitts ‘A Logical Calculus of Ideas Immanent in Nervous Activity’ Macroscopic Intelligence Digital Computing Microscopic Intelligence John von Neumann Marvin Minsky Frank Rosenblatt 1950 First Digital Computers Black Box AI (LISP etc) Perceptron Adaline 1960 Main Frames Theorem Solver Minsky and Papert publish ‘Perceptrons’ Vax Computer (Time Sharing) 1970 Expert Systems The Neural ‘Dark Ages’ Workstations 1980 John Hopfield Maturation of Expert Systems Microcomputers Rumelhart, McClelland & Hinton 1990 Robert Hecht-Nielsen Desktop Supercomputers Practical Applications of Neural Networks

  14. Introduction to ArtificialNeural Networks

  15. Artificial Neural Networks • Inspired by the low level structure of the brain. • Large numbers of simple processors (neurons) joined together by links of various strengths • Can be built in special hardware • Normally (to date) simulated on Von Neumann computers

  16. Tractable Architectures • Feedforward Neural Networks • Connections in one direction only • Partial biological justification • Complex models with constraints (Hopfield and ART). • Feedback loops included • Complex behavior, limited by constraining architecture

  17. Neural Network Taxonomies Supervised Training Unsupervised Training Perceptron/ Multi-Layer Perceptron Kohonen Self-Organising Map ART 2 Others Radial Basis Function Bayesian Methods

  18. Multilayer Perceptron • Multi-layer feedforward Neural Networks are the most popular architecture in use today. • They have the following features: • Theoretical capability to solve any classification problem • Theoretical capability to learn any classification problem • Stability

  19. Output Values Input Signals (External Stimuli) Fig. 1: Multilayer Perceptron Output Layer Adjustable Weights Input Layer

  20. Types of Layer • The input layer. • Introduces input values into the network. • No activation function or other processing. • The hidden layer(s). • Perform classification of features • Two hidden layers are sufficient to solve any problem • Features imply more layers may be better

  21. Types of Layer (continued) • The output layer. • Functionally just like the hidden layers • Outputs are passed on to the world outside the neural network.

  22. y1 w1j w2j y2 w3j O y3 yi wij A Simple Model of a Neuron • Each neuron has a threshold value • Each neuron has weighted inputs from other neurons • The input signals form a weighted sum • If the activation level exceeds the threshold, the neuron “fires”

  23. y1 w1j w2j y2 w3j f(x) O y3 yi wij An Artificial Neuron • Each hidden or output neuron has weighted input connections from each of the units in the preceding layer. • The unit performs a weighted sum of its inputs, and subtracts its threshold value, to give its activation level. • Activation level is passed through a sigmoid activation function to determine output.

  24. Mathematical Definition • Number all the neurons from 1 up to N • The output of the j'th neuron is oj • The threshold of the j'th neuron is j • The weight of the connection from unit i to unit j is wij • The activation of the j'th unit is aj • The activation function is written as (x)

  25. Mathematical Definition • Since the activation aj is given by the sum of the weighted inputs minus the threshold, we can write: aj= ( wijoi ) - j i oj = (aj )

  26. Activation functions • Transforms neuron’s input into output. • Features of activation functions: • A squashing effect is required • Prevents accelerating growth of activation levels through the network. • Simple and easy to calculate • Monotonically non-decreasing • order-preserving

  27. 1 (x) = 1 + e -ax Standard activation functions • The hard-limiting threshold function • Corresponds to the biological paradigm • either fires or not • Sigmoid functions ('S'-shaped curves) • The logistic function • The hyperbolic tangent (symmetrical) • Both functions have a simple differential • Only the shape is important

  28. Figure 2: Activation Functions f(x) f(x) f(x) +1 +1 x x x -1 -1 Hard Limiter Ramp Function Sigmoid Function

  29. The bias unit • A simplified version of threshold. • Add an extra unit called the bias unit. • Always has an output of 1.0. • Weights equal to minus the thresholds. • The same as subtracting the thresholds. • The equations can be further simplified: aj= ( wijoi ) i oj = (aj )

  30. Training Algorithms • Adjust neural network weights to map inputs to outputs. • Use a set of sample patterns where the desired output (given the inputs presented) is known. • The purpose is to learn to generalize • Recognize features which are common to good and bad exemplars

  31. Back-Propagation • A training procedure which allows multi-layer feedforward Neural Networks to be trained; • Can theoretically perform “any” input-output mapping; • Can learn to solve linearly inseparable problems.

  32. Activation functions and training • For feedforward networks: • A continuous function can be differentiated allowing gradient-descent. • Back-propagation is an example of a gradient-descent technique. • Reason for prevalence of sigmoid

  33. Training versus Analysis • Understanding how the network is doing what it does • Predicting behavior under novel conditions

  34. Applications • The properties of neural networks define where they are useful. • Can learn complex mappings from inputs to outputs, based solely on samples • Difficult to analyze: firm predictions about neural network behavior difficult; • Unsuitable for safety-critical applications. • Require limited understanding from trainer, who can be guided by heuristics.

  35. Engine management • The behavior of a car engine is influenced by a large number of parameters • temperature at various points • fuel/air mixture • lubricant viscosity. • A major company have used neural networks to dynamically tune an engine depending on current settings.

  36. Signature recognition • Each person's signature is different. • There are structural similarities which are difficult to quantify. • One company have manufactured a machine which recognizes signatures to within a high level of accuracy. • Considers speed in addition to gross shape. • Makes forgery even more difficult.

  37. Sonar target recognition • Distinguish mines from rocks on sea-bed • The neural network is provided with a large number of parameters which are extracted from the sonar signal. • The training set consists of sets of signals from rocks and mines.

  38. Stock market prediction • “Technical trading” refers to trading based solely on known statistical parameters; e.g. previous price • Neural networks have been used to attempt to predict changes in prices. • Difficult to assess success since companies using these techniques are reluctant to disclose information.

  39. Mortgage assessment • Assess risk of lending to an individual. • Difficult to decide on marginal cases. • Neural networks have been trained to make decisions, based upon the opinions of expert underwriters. • Neural network produced a 12% reduction in delinquencies compared with human experts.

  40. Summary • NNs are based on a highly simplified model of neurons in the human brain. • Neurons joined together by uni-directional weighted connections, sum passes through activation function. • Training algorithms allow network weights to be altered based solely upon training patterns.

More Related