The Kanerva Machine: A Generative Distributed Memory

04/05/2018
by   Yan Wu, et al.
0

We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them. Inspired by Kanerva's sparse distributed memory, it has a robust distributed reading and writing mechanism. The memory is analytically tractable, which enables optimal on-line compression via a Bayesian update-rule. We formulate it as a hierarchical conditional generative model, where memory provides a rich data-dependent prior distribution. Consequently, the top-down memory and bottom-up perception are combined to produce the code representing an observation. Empirically, we demonstrate that the adaptive memory significantly improves generative models trained on both the Omniglot and CIFAR datasets. Compared with the Differentiable Neural Computer (DNC) and its variants, our memory model has greater capacity and is significantly easier to train.

READ FULL TEXT

page 7

page 11

research
02/05/2019

TzK: Flow-Based Conditional Generative Model

We formulate a new class of conditional generative models based on proba...
research
12/01/2022

Why Are Conditional Generative Models Better Than Unconditional Ones?

Extensive empirical evidence demonstrates that conditional generative mo...
research
05/03/2023

Shap-E: Generating Conditional 3D Implicit Functions

We present Shap-E, a conditional generative model for 3D assets. Unlike ...
research
07/30/2020

Rewriting a Deep Generative Model

A deep generative model such as a GAN learns to model a rich set of sema...
research
11/23/2018

Learning Attractor Dynamics for Generative Memory

A central challenge faced by memory systems is the robust retrieval of a...
research
02/20/2021

Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory

Episodic and semantic memory are critical components of the human memory...
research
03/29/2023

HoloDiffusion: Training a 3D Diffusion Model using 2D Images

Diffusion models have emerged as the best approach for generative modeli...

Please sign up or login with your details

Forgot password? Click here to reset