(en) In this presentation, Ahlad Kumar demonstrates the use of a GAN in Google Colab
(fr) Dans cette présentation, Ahlad Kumar démontre l’utilisation d’un GAN dans Google Colab (en anglais)
Google Research: BERT, or Bidirectional Encoder Representations from Transformers
BERT, or Bidirectional Encoder Representations from Transformers, is a new method of pre-training language representations which obtains state-of-the-art results on a wide array of Natural Language Processing (NLP) tasks.
Our academic paper which describes BERT in detail and provides full results on a number of tasks can be found here: https://arxiv.org/abs/1810.04805.
https://github.com/google-research/bert/blob/master/README.md
Open-sourcing PyText for faster NLP development
To make it easier to build and deploy natural language processing (NLP) systems, we are open-sourcing PyText, a modeling framework that blurs the boundaries between experimentation and large-scale deployment. PyText is a library built on PyTorch, our unified, open source deep learning framework.
https://code.fb.com/ai-research/pytext-open-source-nlp-framework/
Google’s on-device text classification AI achieves 86.7% accuracy | VentureBeat
In a paper presented this week at the Conference on Empirical Methods in Natural Language Processing in Brussels, Belgium, Google researchers described offline, on-device AI systems — Self-Governing Neural Networks (SGNNs) — that achieve state-of-the-air results in specific dialog-related tasks.
“The main challenges with developing and deploying deep neural network models on-device are (1) the tiny memory footprint, (2) inference latency and (3) significantly low computational capacity compared to high-performance computing systems, such as CPUs, GPUs, and TPUs on the cloud,” the team wrote.
Machine Learning cheatsheets for Stanford’s CS 229
Afshine Amidi (Ecole Centrale Paris, MIT) et Shervine Amidi (Ecole Centrale Paris, Stanford University) nous offre ici la traduction en français des cheatsheet du cours de machine learning de Stanford (https://stanford.edu/%7Eshervine/teaching/cs-229.html)
https://github.com/afshinea/stanford-cs-229-machine-learning
How is GloVe different from word2vec?
https://www.quora.com/How-is-GloVe-different-from-word2vec
| How is GloVe different from word2vec? – Quora www.quora.com Both models learn geometrical encodings (vectors) of words from their co-occurrence information (how frequently they appear together in large text corpora). They differ in that word2vec is a « predictive » model, whereas GloVe is a « count-based » mod… |