Predictive Coding beyond Gaussian Distributions
Nov 28, 2022
Speakers
Luca Pinchetti
Speaker · 0 followers
Tommaso Salvatori
Speaker · 0 followers
Yordan Yordanov
Speaker · 0 followers
Beren Millidge
Speaker · 0 followers
Yuhang Song
Speaker · 0 followers
Thomas Lukasiewicz
Speaker · 2 followers
About
A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP). A prominent example is predictive coding (PC), which is a neuroscience-inspired method that performs inference on hierarchical Gaussian generative models. These methods, however, fail to keep up with modern neural networks, as they are unable to replicate the dynamics of complex layers and activation functions. In this work, we solve this problem by generalizing PC to arbitrary probability distributions, enabling the training of architectures, such as transformers, that are hard to approximate with only Gaussian assumptions. We perform three experimental analyses. First, we study the gap between our method and the standard formulation of PC on multiple toy examples. Second, we test the reconstruction quality on variational autoencoders, where our method reaches the same reconstruction quality as BP. Third, we show that our method allows us to train transformer networks and achieve performance comparable with BP on conditional language models. More broadly, this method allows neuroscience-inspired learning to be applied to multiple domains, since the internal distributions can be flexibly adapted to the data, tasks, and architectures used.A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP). A prominent example is predictive coding (PC), which is a neuroscience-inspired method that performs inference on hierarchical Gaussian generative models. These methods, however, fail to keep up with modern neural networks, as they are unable to replicate the dynamics of complex layers and activation functions. In this work…
Organizer
NeurIPS 2022
Account · 954 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
OPEN: Orthogonal Propagation with Ego-Network Modeling
Watch later
Liang Yang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Lagrangian Duality Approach to Active Learning
Watch later
Juan Elenter, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing remarks & awards
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Generating Long Videos of Dynamic Scenes
Watch later
Tim Brooks, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Constants of motion network (COMET)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration
Watch later
Fanghui Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%