The Unreasonable Effectiveness of Transfer Learning

Author(s): Satyam Kumar

Originally published on Towards AI.

Essential guide to multi-output prediction with Keras Functional API

This member-only story is on us. Upgrade to access all of Medium.

Image by Gerd Altmann from Pixabay

Training a complex deep-learning neural network requires significant computational efficiency, the availability of a large corpus of data, and better feature learning architecture to achieve state-of-the-art results. But these requirements are only sometimes satisfied for start-ups, researchers, and students. With the recent advancement of deep learning, many pre-trained models are now open-sourced.

Some of the popular convolution neural network-based pre-trained models are VGG16/19, ResNet, MobileNet, EfficientNet, ResNeXt, and many more. The weights and the architecture of these pre-trained models can be tuned to use them… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI