Published in


Fujitsu AI, Tokyo U & RIKEN AIP Study Decomposes DNNs Into Modules That Can Be Recomposed Into New Models for Other Tasks

Deep neural networks (DNNs) have achieved astonishing performance on many complex tasks, but a major obstacle impeding their wider application remains the requirement for resource-consuming model retraining every time the task and the subclasses to be classified change.




We produce professional, authoritative, and thought-provoking content relating to artificial intelligence, machine intelligence, emerging technologies and industrial insights.

Recommended from Medium

Cross Validation: Option to get rid of Data Issues for Training the Model


Deep Contractive Auto Encoder in Keras

String to Datetime

Predicting user churn using Apache Spark

Computational Complexity of SVM

Jovian.ML Assignment-1 Blog Post

Introduction to Gaussian Process Regression (GPR)

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


AI Technology & Industry Review — | Newsletter: | Share My Research | Twitter: @Synced_Global

More from Medium

Princeton U’s DataMUX Enables DNNs to Simultaneously and Accurately Process up to 40 Input…

Interaction-Grounded Learning: Learning from feedback, not rewards

DeepMind and OpenAI Ideas to Incorporate Human Feedback in Reinforcement Learning Agents

Why Is Cross Entropy Equal to KL-Divergence?