Timezone: »

 
Poster
Weight Agnostic Neural Networks
Adam Gaier · David Ha

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #149
in Neuroscience and Cognitive Science -- Neuroscience »

Not all neural network architectures are created equal, some perform much better than others for certain tasks. But how important are the weight parameters of a neural network compared to its architecture? In this work, we question to what extent neural network architectures alone, without learning any weight parameters, can encode solutions for a given task. We propose a search method for neural network architectures that can already perform a task without any explicit weight training. To evaluate these networks, we populate the connections with a single shared weight parameter sampled from a uniform random distribution, and measure the expected performance. We demonstrate that our method can find minimal neural network architectures that can perform several reinforcement learning tasks without weight training. On a supervised learning domain, we find network architectures that achieve much higher than chance accuracy on MNIST using random weights.

Interactive version of this paper at https://weightagnostic.github.io/

Keywords: Neuroscience and cognitive science · Deep Learning -> Biologically Plausible Deep Networks; Neuroscience and Cognitive Science · Connectomics; Neuroscience and Cog
[ Paper]  [ Slides] 

Author Information

Adam Gaier (Google / Inria / H-BRS)
David Ha (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors