An adversarial algorithm for variational inference with a new role for acetylcholine

06/18/2020
by   Ari S. Benjamin, et al.
0

Sensory learning in the mammalian cortex has long been hypothesized to involve the objective of variational inference (VI). Likely the most well-known algorithm for cortical VI is the Wake-Sleep algorithm (Hinton et al. 1995). However Wake-Sleep problematically assumes that neural activities are independent given lower-layers during generation. Here, we construct a VI system that is both compatible with neurobiology and avoids this assumption. The core of the system is a wake-sleep discriminator that classifies network states as inferred or self-generated. Inference connections learn by opposing this discriminator. This adversarial dynamic solves a core problem within VI, which is to match the distribution of stimulus-evoked (inference) activity to that of self-generated activity. Meanwhile, generative connections learn to predict lower-level activity as in standard VI. We implement this algorithm and show that it can successfully train the approximate inference network for generative models. Our proposed algorithm makes several biological predictions that can be tested. Most importantly, it predicts a teaching signal that is remarkably similar to known properties of the cholinergic system.

READ FULL TEXT

page 5

page 16

research
06/28/2019

The Thermodynamic Variational Objective

We introduce the thermodynamic variational objective (TVO) for learning ...
research
07/24/2019

On the relationship between variational inference and adaptive importance sampling

The importance weighted autoencoder (IWAE) (Burda et al., 2016) and rewe...
research
07/14/2023

Brain in the Dark: Design Principles for Neuro-mimetic Learning and Inference

Even though the brain operates in pure darkness, within the skull, it ca...
research
07/06/2020

Learning to learn generative programs with Memoised Wake-Sleep

We study a class of neuro-symbolic generative models in which neural net...
research
10/19/2015

Accelerometer based Activity Classification with Variational Inference on Sticky HDP-SLDS

As part of daily monitoring of human activities, wearable sensors and de...
research
12/09/2020

Binding and Perspective Taking as Inference in a Generative Neural Network Model

The ability to flexibly bind features into coherent wholes from differen...
research
08/16/2003

Controlled hierarchical filtering: Model of neocortical sensory processing

A model of sensory information processing is presented. The model assume...

Please sign up or login with your details

Forgot password? Click here to reset