Keywords: Inductive Bias, Generalisation, Meta-Learning, Spiking Neural Network, Neuroscience
TL;DR: We meta-learn functions that networks of interest find easy to generalise, characterising their inductive bias; we suggest this as a method for interpreting and understanding network function.
Abstract: Animals receive noisy and incomplete information, from which we must learn how to react in novel situations. A fundamental problem is that training data is always finite, making it unclear how to generalise to unseen data. But, animals do react appropriately to unseen data, wielding Occam's razor to select a parsimonious explanation of the observations. How they do this is called their inductive bias, and it is implicitly built into the operation of animals' neural circuits. This relationship between an observed circuit and its inductive bias is a useful explanatory window for neuroscience, allowing design choices to be understood normatively. However, it is generally very difficult to map circuit structure to inductive bias. In this work we present a neural network tool to bridge this gap. The tool allows us to meta-learn the inductive bias of neural circuits by learning functions that a neural circuit finds easy to generalise, since easy-to-generalise functions are exactly those the circuit chooses to explain incomplete data. We show that in systems where the inductive bias is known analytically, i.e. linear and kernel regression, our tool recovers it. Then, we show it is able to flexibly extract inductive biases from differentiable circuits, including spiking neural networks. This illustrates the intended use case of our tool: understanding the role of otherwise opaque pieces of neural functionality, such as non-linearities, learning rules, or connectomic data, through the inductive bias they induce.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)