Regularized evolution for image classifier architecture search

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have...

Top 10 data science libraries in Python

Python is considered to be the easiest language to learn for beginners. Not only that, but Python is also popular because of the dynamic...

SIMMC: A data set for developing next-generation shopping assistants

What it is Situated and Interactive Multimodal Conversations (SIMMC) is a first-of-its-kind data set that has been open-sourced to help researchers and engineers develop virtual...

Improving skin-disease classification based on customized loss function

Skin cancer is one of the most common cancers in the world. However, the disease is curable if detected in the beginning stage. Early...

10 read-worthy books on Data Science and Machine Learning

Never before had free and open-source software experienced such a boom. For those who are interested in Machine Learning and Data Science (mostly with...

MediaPipe Iris: Real-time Iris tracking & Depth estimation

A wide range of real-world applications, including computational photography (e.g., portrait mode and glint reflections) and augmented reality effects (e.g., virtual avatars) rely on estimating eye position by...

Open-sourcing PyText for faster NLP development

PyText is a library built on PyTorch, our unified, open-source deep learning framework. It offers several benefits for NLP development: Simplified workflow for faster experimentation. ...

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

Machine learning research has advanced in multiple aspects, including model structures and learning methods. The effort to automate such research, known as AutoML, has...

New state-of-the-art voice separation model that distinguishes multiple speakers

We’re introducing a new method to separate up to five voices speaking simultaneously on a single microphone. Our method surpasses previous state-of-the-art performance on...