Temporal-related Convolutional-Restricted-Boltzmann-Machine capable of learning relational order via reinforcement learning procedure?

by   Zizhuang Wang, et al.

In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly related, so it is wise to make multiplicative unit learn relations among more input maps, in other words, to find the optimal relational-order of each unit. In order to enable our machine to learn relational order, we developed a reinforcement-learning method whose optimality is proven to train the network.



page 1

page 2

page 3

page 4


Reinforcement Learning Using Quantum Boltzmann Machines

We investigate whether quantum annealers with select chip layouts can ou...

Learning Relational Rules from Rewards

Humans perceive the world in terms of objects and relations between them...

Restricted Boltzmann machine to determine the input weights for extreme learning machines

The Extreme Learning Machine (ELM) is a single-hidden layer feedforward ...

Non-Parametric Learning of Lifted Restricted Boltzmann Machines

We consider the problem of discriminatively learning restricted Boltzman...

Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines

Reinforcement learning has driven impressive advances in machine learnin...

Theta-RBM: Unfactored Gated Restricted Boltzmann Machine for Rotation-Invariant Representations

Learning invariant representations is a critical task in computer vision...

Demystifying Relational Latent Representations

Latent features learned by deep learning approaches have proven to be a ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.