Log In Sign Up

A Similarity-preserving Neural Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuit

by   Yanis Bahroun, et al.

Learning to detect content-independent transformations from data is one of the central problems in biological and artificial intelligence. An example of such problem is unsupervised learning of a visual motion detector from pairs of consecutive video frames. Rao and Ruderman formulated this problem in terms of learning infinitesimal transformation operators (Lie group generators) via minimizing image reconstruction error. Unfortunately, it is difficult to map their model onto a biologically plausible neural network (NN) with local learning rules. Here we propose a biologically plausible model of motion detection. We also adopt the transformation-operator approach but, instead of reconstruction-error minimization, start with a similarity-preserving objective function. An online algorithm that optimizes such an objective function naturally maps onto an NN with biologically plausible learning rules. The trained NN recapitulates major features of the well-studied motion detector in the fly. In particular, it is consistent with the experimental observation that local motion detectors combine information from at least three adjacent pixels, something that contradicts the celebrated Hassenstein-Reichardt model.


page 2

page 3

page 5

page 6

page 10

page 11

page 12

page 13


A Normative and Biologically Plausible Algorithm for Independent Component Analysis

The brain effortlessly solves blind source separation (BSS) problems, bu...

A biologically plausible neural network for Slow Feature Analysis

Learning latent features from time series data is an important problem i...

Neuroscience-inspired online unsupervised learning algorithms

Although the currently popular deep learning networks achieve unpreceden...

A Neural Network with Local Learning Rules for Minor Subspace Analysis

The development of neuromorphic hardware and modeling of biological neur...

2D-Motion Detection using SNNs with Graphene-Insulator-Graphene Memristive Synapses

The event-driven nature of spiking neural networks makes them biological...

Unsupervised learning of depth and motion

We present a model for the joint estimation of disparity and motion. The...