Composed of many “neurons” that co-operate to perform the desired function Models of the brain and nervous system Highly parallel ◦ Process information much more like the brain than a serial computer Learning Very simple principles Very complex behaviours Applications ◦ As powerful problem solvers ◦ As biological models
An Artificial Neural Network is a network of many very simple processors, each possibly having a local memory. Theunits are connected by unidirectional communication channels, which carry numeric data. Theunits operate only on their local data and on the inputs they receive via the connections.
Classification Pattern recognition, feature extraction, image matching Noise Reduction Recognize patterns in the inputs and produce noiseless outputs Prediction Extrapolation based on historical data
Ability to learn NN’s figure out how to perform their function on their own Determine their function based only upon sample inputs Ability to generalize i.e. produce reasonable outputs for inputs it has not been taught how to deal with
A neuron: many-inputs / one- output unit Dendrites receive activation from other neurons Axons act as transmission lines to send activation to other neurons Synapses ,the junctions allow signal transmission between the axons and dendrites
ANNs incorporate the two fundamental components of biological neural nets:1. Neurones (nodes)2. Synapses (weights)
Neuron consists of three basic components. 1 . Weights 2 . Thresholds 3 . Activation function
Weighting Factors The values w1,w2,…wn are weights to determine thestrength of input vector x=[x1,x2,…xn]T Thresholds The node’s internal threshold is the magnitude offset Activation Function Performs a mathematical operation on the signal output Most common are linear,threshold,S shaped,tangenthyperbolic function Choice of function depend on the problem solved by theneural network
Neural Networks offer improved performance over conventional technologies in areas which includes: Machine Vision Robust Pattern Detection Signal Filtering Virtual Reality Artificial Life and more.
Advantages ◦ Adapt to unknown situations ◦ Robustness: fault tolerance due to network redundancy ◦ Autonomous learning and generalization Disadvantages ◦ Not exact ◦ Large complexity of the network structure
Learning the Distribution of Object Trajectories for Event Recognition Radiosity for Virtual Reality Systems Speechreading (Lipreading) Detection and Tracking of Moving Targets Real-time Target Identification for Security Applications Autonomous Walker & Swimming Eel
Robocup: Robot World Cup Using HMMs (hidden Markov models) for Audio-to-Visual Conversion Artificial Life: Galapagos
The moving target detection and track methods here are "track before detect" methods. They correlate sensor data versus time and location, based on the nature of actual tracks. The track statistics are "learned" based on artificial neural network (ANN) training with prior real or simulated data. (a) Raw input backgrounds with weak targets included, (b) Detected target sequence at the ANN processing output, post-detection tracking not included
As part of the research program Neuroinformatik the IPVR develops a neural speechreading system as part of a user interface for a workstation. A neural classifier detects visibility of teeth edges and other attributes. At this stage of the approach the edge between the closed lips is automatically modeled if applicable, based on a neural networks decision.
The system localises and tracks peoples faces as they move through a scene. It integrates the following techniques: 1. Motion detection 2. Tracking people based upon motion 3. Tracking faces using an appearance model Faces are tracked robustly by integrating motion and model-based tracking.
(A) Tracking in low resolution and poor (B) Tracking two peoplelighting conditions simultaneously: lock is maintained on the faces despite unreliable motion-based body tracking.