Sparse Training Theory for Scalable and Efficient Agents

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud, they suffer from computational and memory limitations, and they cannot be used to model adequately large physical worlds for agents which assume networks with billions of neurons. These issues are addressed in the last few years by the emerging topic of sparse training, which trains sparse networks from scratch. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions which has the potential of alleviating sparse training limitations to push deep learning scalability well beyond its current boundaries. Nevertheless, the theoretical advancements impact in complex multi-agents settings is discussed from a real-world perspective, using the smart grid case study.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/15/2023

Sampling-Based Techniques for Training Deep Neural Networks with Limited Computational Resources: A Scalability Evaluation

Deep neural networks are superior to shallow networks in learning comple...
research
03/23/2022

Resource allocation optimization using artificial intelligence methods in various computing paradigms: A Review

With the advent of smart devices, the demand for various computational p...
research
02/02/2021

Truly Sparse Neural Networks at Scale

Recently, sparse training methods have started to be established as a de...
research
06/17/2018

How Could Polyhedral Theory Harness Deep Learning?

The holy grail of deep learning is to come up with an automatic method t...
research
10/01/2021

Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration

Deep learning has powered recent successes of artificial intelligence (A...
research
04/13/2021

Podracer architectures for scalable Reinforcement Learning

Supporting state-of-the-art AI research requires balancing rapid prototy...

Please sign up or login with your details

Forgot password? Click here to reset