This paper introduces gradient descent methods applied to meta-leaming (leaming how to leam) in Neural Networks. Meta-leaning has been of interest in the machine leaming field for decades because of its appealing applications to intelligent agents, non-stationary time series, autonomous robots, and improved leaming algorithms. Many previous neural network-based approaches toward meta-leaming ha...

In this paper, we aim to develop alternative methods to backpropagation that more closely resemble biological computation. While backpropagation has been an extremely valuable tool in machine learning applications, there is no evidence that neurons can back propagate errors. We propose two methods intended to model the intrinsic selectivity of biological neurons to certain features. Both method...

Two remarkable aspects of pyramidal neurons are their complex dendritic morphologies and the abundant presence of spines, small structures that are the sites of excitatory input. Although the channel properties of the dendritic shaft membrane have been experimentally probed, the influence of spine properties in dendritic signaling and action potential propagation remains unclear. To explore thi...

We measured the action potential backpropagation delays in apical dendrites of layer V pyramidal neurons of the somatosensory cortex under different stimulation regimes that exclude synaptic involvement. These delays showed robust features and did not correlate to either transient change in the stimulus strength or low frequency stimulation of suprathreshold membrane oscillations. However, our ...

This paper deals with the predictive compression of images using neural networks (NN). The idea is to use of the backpropagation algorithm in order to compute the predicted pixels. The results validation is performed by comparison with linear prediction compression used in JPEG algorithm. Key-Words: lossless image compression, neural networks, prediction, backpropagation algorithm

We present a technique, which we term leapfrogging, to parallelize backpropagation in deep neural networks. We show that this technique yields a savings of 1 − 1/k of a dominant term in backpropagation, where k is the number of threads (or gpus).

Derivation of backpropagation in convolutional neural network (CNN) is conducted based on an example with two convolutional layers. The step-by-step derivation is helpful for beginners. First, the feedforward procedure is claimed, and then the backpropagation is derived based on the example. 1 Feedforward

Backpropagation based on minimization algorithms is replaced by heuristic search techniques for quantized weights. The resulting algorithm is fast, avoids local minima of the cost function, and may be used either as initialization method for standard backpropagation or as a logical rule extraction technique.

A number of different data sets are used to compare a variety of neural network training algorithms: backpropagation, quickprop, committees of backpropagation style networks and Cascade Correlation. The results are further compared with a decision tree technique, C4.5, to assess which types of problems are more suited to the different classes of inductive learning algorithms.

This paper presents an energy back-propagation algorithm (EBP). Learning and convergence processes of the standard backpropagation algorithm (SBP) are based on the energy function. The energy function is used with the convergence process to extract the nearest image for the unknown tested image. The EBP algorithm shows considerably better performance in terms of time of learning, time of conver...