Day: December 2, 2019

The Masakhane project wants machine translation and AI to transform Africa
AI Natural Language Processing TensorFlow

The Masakhane project Wants Machine Translation & AI to Transform Africa

Here’s an interesting project involving two of my favorite topics: language and AI. Some estimates put the number of living languages on the continent at 2,000 or more. This can stand in the way of communication, as well as commerce, and earlier the year led to the creation of the Masakhane open source project, an […]

Read More
AI Can See. Can We Teach It To Feel?
Computer Vision TensorFlow

Now that AI Can See, Can We Teach It To Feel?

The last few years have seen great strides in the field of computer vision, but what comes next? Can we teach AI to “feel” something about what it sees? The folks at Getty Images think we can. At first blush, the idea that AI could “feel” something would seem to be pretty far-fetched. Feelings in […]

Read More
How To Build A BERT Classifier Model With TensorFlow 2.0
Natural Language Processing TensorFlow

How To Build A BERT Classifier Model With TensorFlow 2.0

BERT is one of the most popular algorithms in the NLP spectrum known for producing state-of-the-art results in a variety of language modeling tasks. Built on top of transformers and seq-to-sequence models, the Bidirectional Encoder Representations from Transformers is a powerful NLP modeling technique that sits at the cutting edge. Here’s a great write up […]

Read More
AI Machine Learning Startups

Startup Showcase at MLADS

Microsoft for Startups shares this highlight reel from the Spring MLADS conference. In case you’re not familiar with MLADS, check out Data Driven’s coverage of the most recent one. Twice a year, Microsoft assembles over 4,000 of our top data scientists and engineers for a two day internal conference to explore the state of the […]

Read More
Deep Learning Reinforcement Learning

Why Deep Q Learning Needs A Target Network and Replay Memory

Machine Learning with Phil has got another interesting look at Deep Q Learning as part of a preview of his course. The two biggest innovations in deep Q learning were the introduction of the target network and the replay memory. One would think that simply bolting a deep neural network to the Q learning algorithm […]

Read More
AI Autonomous Vehicles Drones

Autonomous Systems, Aerial Robotics and Game of Drones

Microsoft Research marks its 100th episode with with Gurdeep Pall and Dr. Ashish Kapoor talking about autonomous systems. There’s a lot of excitement around self-driving cars, delivery drones, and other intelligent, autonomous systems, but before they can be deployed at scale, they need to be both reliable and safe. That’s why Gurdeep Pall, CVP of […]

Read More

Noam Chomsky on Language, Cognition, and Deep Learning

Lex Fridman keeps landing the “big fish” on his podcast. This time, he sits down with Noam Chomsky. Noam Chomsky is one of the greatest minds of our time and is one of the most cited scholars in history. He is a linguist, philosopher, cognitive scientist, historian, social critic, and political activist. He has spent […]

Read More
AI Reinforcement Learning

Naive Actor Critic With Experience Replay

Machine Learning with Phil posted this tutorial to apply experience replay to the actor critic algorithm. It seems smart, but it turns out that it doesn’t work. Despite the fact that the replay memory is critical to the success of the deep Q learning algorithm, it completely breaks the actor critic network.

Read More