Back propagation (Artificial intelligence)

The gripping action as performed by an average person is developed over their life and
changes over time. The initial learning is based on trial and error and becomes a natural
action which is modified as the physiology of the individual changes. Each grip type is a
personal expression and as the grip changes over time to accommodate physiologically
changes, it can be considered to be a grip-signature. lt is postulated that an ANN can deliver a classification mechanism that is able to make
sense of the varying gripping inputs that are linearly inseparable and uniquely attributed
to user physiology. Succinctly, in this design, the stifnulus is characterized by a voltage
that represents the applied force in a grip. This signature of forces is then used to train an
ANN to recognize the grip that produced the signature, the ANN in turn is used to
successfully classify three unique states of grip-signatures collected from the gripping
action of various individuals as they hold, lift and crush a paper coffee-cup. A comparative study is done for three types of classification: K-Means, Backpropagation
Feedforward Neural Networks and Recurrent Neural Networks, with recommendations
made in selecting more effective classification methods.

An artificial neural network is used to predict the stable geometry of alluvial rivers. This knowledge is useful for the design of new channels or modification of natural rivers. Given inputs of river discharge, slope and mean particle size, an artificial neural network is trained to predict the corresponding stable channel width and depth. The network is trained using data from several alluvial canals and rivers. Various factors including training set size and composition, number of hidden layer nodes, activation function type, and data scaling method are analyzed as variables affecting network performance. These factors are studied to determine impacts on network accuracy and generalizing ability.

Backpropagation is a standard algorithm that is widely employed in many neural networks. Due to its wide acceptance and implementation, a standard benchmark for evaluating the performance of the algorithm is a handy tool for software design and development. The object of this thesis is to propose the use of the classic XOR problem for the performance evaluation of the backpropagation algorithm, with some variations on the input data sets. This thesis covers background work in this area and discusses the results obtained by other researchers. A series of test cases are then developed and run to perform the performance analysis of the backpropagation algorithm. As the performance of the networks depends strongly on the inputs, the effect of variation of the design parameters for the networks are evaluated and discussed.