Neuron Selectivity as a Biologically Plausible Alternative to Backpropagation
نویسندگان
چکیده
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 methods use selectivity matrices to calculate error and to update synaptic weights in different ways, either by comparing neuronal firing rate to a threshold firing rate algorithm or computing error from a generated score scoring algorithm. We trained and tested networks that used either of the two algorithms with the MNIST database. We compared their performance with a multilayer perceptron network with 3 hidden layers that updated synaptic weights through typical error backpropagation. The backpropagation algorithm had a test error of 1.7%. Networks that updated synaptic weights based on the scoring method gave a test error of 2.0%, and networks using the firing rate method 4.3%. We were thus able to develop more biologically plausible models of neural networks in the brain while obtaining performance comparable to typical backpropagation algorithms.
منابع مشابه
From artificial neural networks to spiking neuron populations and back again
In this paper, we investigate the relation between Artificial Neural Networks (ANNs) and networks of populations of spiking neurons. The activity of an artificial neuron is usually interpreted as the firing rate of a neuron or neuron population. Using a model of the visual cortex, we will show that this interpretation runs into serious difficulties. We propose to interpret the activity of an ar...
متن کاملRoad Sign Recognition by Single Positioning of Space-Variant Sensor Window
A biologically plausible model of traffic sign detection and recognition invariantly with respect to variable viewing conditions is presented. The model simulates several key mechanisms of biological vision, such as space-variant representation of information (reduction in resolution from the fovea to retinal periphery), orientation selectivity in the cortical neuron responses, and context enco...
متن کاملSelf-organization in a Simple Task of Motor Control Based on Spatial Encoding
This paper elaborates on the possibilities for self-adjustment of a biological neural network used as feedback controller in the motor control system of a six-legged walker. As biological systems, in contrast to technical systems, show an impressive capability of self-adaptation, this is meant as a proof of principle. Complementing an intensity encoded system (Linder, 2002), where scalar values...
متن کاملCan Simple Cells Learn Curves? A Hebbian Model in a Structured Environment
In the mammalian visual cortex, orientation-selective 'simple cells' which detect straight lines may be adapted to detect curved lines instead. We test a biologically plausible, Hebbian, single-neuron model, which learns oriented receptive fields upon exposure to unstructured (noise) input and maintains orientation selectivity upon exposure to edges or bars of all orientations and positions. Th...
متن کاملBidirectional Activation-based Neural Network Learning Algorithm
We present a model of a bidirectional three-layer neural network with sigmoidal units, which can be trained to learn arbitrary mappings. We introduce a bidirectional activation-based learning algorithm (BAL), inspired by O’Reilly’s supervised Generalized Recirculation (GeneRec) algorithm that has been designed as a biologically plausible alternative to standard error backpropagation. BAL shares...
متن کامل