Evolutionary training of hardware realizable multilayer perceptrons

The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks, provides tolerance to noise and improves the interpretation of the internal representations. In certain case, such as in learning stationary tasks, it may be sufficient to find appropriate weights for an MLP with threshold activation functions by software simulation and, then, transfer the weight values to the hardware implementation. Efficient training of these networks is a subject of considerable ongoing research. Methods available in the literature mainly focus on two-state (threshold) nodes and try to train the networks by approximating the gradient of the error function and modifying appropriately the gradient descent, or by progressively altering the shape of the activation functions. In this paper, we propose an evolution-motivated approach, which is eminently suitable for networks with threshold functions and compare its performance with four other methods. The proposed evolutionary strategy does not need gradient related information, it is applicable to a situation where threshold activations are used from the beginning of the training, as in “on-chip” training, and is able to train networks with integer weights.     

Improving the performance of convolutional neural network for skin image classification using the response of image analysis filters

Neural Computing and Applications - In this work, we focus in the analysis of dermoscopy images using convolutional neural networks (CNNs). More specifically, we investigate the value of augmenting...     

Real time vision-based measurements for quality control of industrial rods on a moving conveyor

This work proposes a fully automated approach for vision-based quality control of manufactured metal rods. The proposed approach is able to detect the main axis of the rod and calculate its curvature, versus specifications. The proposed algorithm utilizes video acquired in real time by a single mono-ocular USB camera. A signal processing module identifies in real time the video frame that images the rod at the appropriate position on the conveyor. Initialization of the algorithm can take place either manually, or by utilizing the calibration of the camera. Concurrently, the image processing module estimates the curvature of the rod using its medial axis, to classify the rod as normal or defect. Initial results show that the proposed algorithm can operate in real time with very high accuracy under controlled illumination conditions and backgrounds. This methodology is capable of processing video at 30 frames per second, using a general purpose laptop.     

Globally Convergent Modification of the Quickprop Method

A mathematical framework for the convergence analysis of the well-known Quickprop method is described. Furthermore, we propose a modification of this method that exhibits improved convergence speed and stability, and, at the same time, alleviates the use of heuristic learning parameters. Simulations are conducted to compare and evaluate the performance of the new modified Quickprop algorithm with various popular training algorithms. The results of the experiments indicate that the increased convergence rates achieved by the proposed algorithm, affect by no means its generalization capability and stability.     

Globally convergent algorithms with local learning rates

A novel generalized theoretical result is presented that underpins the development of globally convergent first-order batch training algorithms which employ local learning rates. This result allows us to equip algorithms of this class with a strategy for adapting the overall direction of search to a descent one. In this way, a decrease of the batch-error measure at each training iteration is ensured, and convergence of the sequence of weight iterates to a local minimizer of the batch error function is obtained from remote initial weights. The effectiveness of the theoretical result is illustrated in three application examples by comparing two well-known training algorithms with local learning rates to their globally convergent modifications.     

Parallel evolutionary training algorithms for “hardware-friendly” neural networks

In this paper, Parallel Evolutionary Algorithms for integer weightneural network training are presented. To this end, each processoris assigned a subpopulation of potential solutions. Thesubpopulations are independently evolved in parallel andoccasional migration is employed to allow cooperation betweenthem. The proposed algorithms are applied to train neural networksusing threshold activation functions and weight values confined toa narrow band of integers. We constrain the weights and biases inthe range [–3, 3], thus they can be represented by just 3 bits.Such neural networks are better suited for hardware implementationthan the real weight ones. These algorithms have been designedkeeping in mind that the resulting integer weights require lessbits to be stored and the digital arithmetic operations betweenthem are easier to be implemented in hardware. Another advantageof the proposed evolutionary strategies is that they are capableof continuing the training process ``on-chip', if needed. Ourintention is to present results of parallel evolutionaryalgorithms on this difficult task. Based on the application of theproposed class of methods on classical neural network problems,our experience is that these methods are effective and reliable.     

Neural network-based colonoscopic diagnosis using on-line learning and differential evolution

In this paper, on-line training of neural networks is investigated in the context of computer-assisted colonoscopic diagnosis. A memory-based adaptation of the learning rate for the on-line back-propagation (BP) is proposed and used to seed an on-line evolution process that applies a differential evolution (DE) strategy to (re-) adapt the neural network to modified environmental conditions. Our approach looks at on-line training from the perspective of tracking the changing location of an approximate solution of a pattern-based, and thus, dynamically changing, error function. The proposed hybrid strategy is compared with other standard training methods that have traditionally been used for training neural networks off-line. Results in interpreting colonoscopy images and frames of video sequences are promising and suggest that networks trained with this strategy detect malignant regions of interest with accuracy.     

Deterministic nonmonotone strategies for effective training of multilayer perceptrons

We present deterministic nonmonotone learning strategies for multilayer perceptrons (MLPs), i.e., deterministic training algorithms in which error function values are allowed to increase at some epochs. To this end, we argue that the current error function value must satisfy a nonmonotone criterion with respect to the maximum error function value of the M previous epochs, and we propose a subprocedure to dynamically compute M. The nonmonotone strategy can be incorporated in any batch training algorithm and provides fast, stable, and reliable learning. Experimental results in different classes of problems show that this approach improves the convergence speed and success percentage of first-order training algorithms and alleviates the need for fine-tuning problem-depended heuristic parameters.     

Distributed computing methodology for training neural networks in an image-guided diagnostic application

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.