Abstract
Recent advances in machine learning have enabled neural networks to solve tasks humans typically perform. These networks offer an exciting new tool for neuroscience that can give us insight in the emergence of neural and behavioral mechanisms. A big gap remains though between the very deep neural networks that have risen in popularity and outperformed many existing shallow networks in the field of computer vision and the highly recurrently connected human brain. This trend towards ever-deeper architectures raises the question why the brain has not developed such an architecture. Besides wiring constraints we argue that the brain operates under different circumstances when performing object recognition, being confronted with noisy and ambiguous sensory input. The role of time in the process of object recognition is investigated, showing that a recurrent network trained through reinforcement learning is able to learn the amount of time needed to arrive at an accurate estimate of the stimulus and develops behavioral and neural mechanisms similar to those found in the human and non-human primate literature.
Highlights
Recent developments in neural networks offer a promising new avenue for studying the mechanisms of the brain
Evidence integration in recurrent neural networks assumptions and components used for the neural network are necessary and sufficient for the emergence of human like behavior and neural mechanisms. We explore these questions by using a perceptual decision making task that is often investigated in humans and non-human primates to study the role of time in perceptual decision making
To see how a recurrent neural network deals with perceptual decision-making under noisy conditions, we used an object recognition task
Summary
Recent developments in neural networks offer a promising new avenue for studying the mechanisms of the brain. Exploring the mechanisms that a neural network develops to solve a particular task can give us valuable insight into the basic ingredients needed for certain complex behaviors to arise This adds an exciting new tool to neuroscience research that can help us to solve questions of ‘how’ and ‘why’ a certain mechanism develops, moving beyond the comparison of purely descriptive models of neural and/or behavioral phenomena. For these neural networks to become a useful tool for studying the brain there is still a big gap to bridge.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
