GoodAI Blog
Published in

GoodAI Blog

Benefits of modular approach — generalization

By Jaroslav Vítků

Usually, in Deep Learning, the tasks are solved by a big monolithic Artificial Neural Network.

Compared to this, one of the properties of the Badger architecture is modularity: instead of using one big neural network, the Badger should be composed of many small Experts which solve the whole task in a collaborative manner. Further assumption is that these Experts share the weights, therefore are identical at the beginning.

Despite the fact that this approach introduces several complications, it has many benefits as well.

Several benefits of modularity include:

  • System is able to dynamically change its size based on the task, therefore Badger should be able to solve tasks normal ANNs are not able to solve.
  • Scaling with number of Experts: we should be able to train on small scale of problem (e.g. small num. Experts) and then deploy to big scale.
  • Modular policies should generalize better (e.g. [Goyal et al, 2020], [Greff et al, 2017]).

This article uses simple experiments to illustrates the following topics:

  1. Ability to train on small version of the task and then being able to deploy to modified versions of the tasks without changing the Expert policy (weights). Policies trained on small robots generalize to robots of different size and/or shape.
  2. In more complicated case, the tasks usually requires the Experts to communicate with each other. One of open questions is how an efficient communication topology should look like and if it is possible to establish it automatically from data.

Code for the experiments available here at github.

Read the full article here.

Originally published at on August 9, 2020.




All the latest news from GoodAI!

Recommended from Medium

Machine Learning Algorithm Mind Map

Understanding Natural Language Processing through Recurrent Neural Networks

MLiterature: Regression Evaluations (R squared)

A Year in Computer Vision — Part 2 of 4

Tuning your Model HyperParameters with AWS SageMaker

Understanding the Expressive Power of Neural Networks

I modeled my co-workers using our office Slack chats. The results were awesomenian.

Unsupervised Question Decomposition for Question Answering

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store


Our mission is to develop general artificial intelligence — as fast as possible — to help humanity and understand the universe

More from Medium

Newsletter #69 — OpenAI takes image generation to the next level with DALL-E-2

Building an artificial brain: 86B neurons, 500T synapses, and a neuromorphic chip

Hollywood is dead, long live Hollywood

GeAI and the need for Content Authenticity