Learning Iterative Reasoning through Energy Minimization

06/30/2022
by   Yilun Du, et al.
9

Deep learning has excelled on complex pattern recognition tasks such as image classification and object recognition. However, it struggles with tasks requiring nontrivial reasoning, such as algorithmic computation. Humans are able to solve such tasks through iterative reasoning – spending more time thinking about harder tasks. Most existing neural networks, however, exhibit a fixed computational budget controlled by the neural network architecture, preventing additional computational processing on harder tasks. In this work, we present a new framework for iterative reasoning with neural networks. We train a neural network to parameterize an energy landscape over all outputs, and implement each step of the iterative reasoning as an energy minimization step to find a minimal energy solution. By formulating reasoning as an energy minimization problem, for harder problems that lead to more complex energy landscapes, we may then adjust our underlying computational budget by running a more complex optimization procedure. We empirically illustrate that our iterative reasoning approach can solve more accurate and generalizable algorithmic reasoning tasks in both graph and continuous domains. Finally, we illustrate that our approach can recursively solve algorithmic problems requiring nested reasoning

READ FULL TEXT

page 7

page 12

research
06/08/2021

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

Deep neural networks are powerful machines for visual pattern recognitio...
research
02/22/2021

Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems

Deep neural networks are powerful machines for visual pattern recognitio...
research
05/30/2019

What Can Neural Networks Reason About?

Neural networks have successfully been applied to solving reasoning task...
research
09/16/2021

Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning

An important aspect of artificial intelligence (AI) is the ability to re...
research
06/29/2020

Switchblade – a Neural Network for Hard 2D Tasks

Convolutional neural networks have become the main tools for processing ...
research
08/25/2021

Subgoal Search For Complex Reasoning Tasks

Humans excel in solving complex reasoning tasks through a mental process...
research
12/14/2015

On non-iterative training of a neural classifier

Recently an algorithm, was discovered, which separates points in n-dimen...

Please sign up or login with your details

Forgot password? Click here to reset