Digests » 26

this week's favorite

BERT – State of the Art Language Model for NLP

BERT (Bidirectional Encoder Representations from Transformers) is a recent paper published by researchers at Google AI Language. It has caused a stir in the Machine Learning community by presenting state-of-the-art results in a wide variety of NLP tasks, including Question Answering (SQuAD v1.1), Natural Language Inference (MNLI), and others.

Gradient Descent Finds Global Minima of Deep Neural Networks

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized neural network with residual connections (ResNet). Our analysis relies on the particular structure of the Gram matrix induced by the neural network architecture.

The Open Images Dataset

We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection.

Tensorspace: neural network visualizer

Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js.

Hidden Markov Model Tutorial

Hidden Markov Models are powerful tools, commonly used in a wide range of applications from stock price prediction, to gene decoding, to speech recognition.This is a tutorial on Hidden Markov Models that I wrote, and thought to would make publicly available for download since I believe it captures the intuition quite well.