How Do Open Source Deep Learning Frameworks Stack Up?

As the popularity of AI and deep learning increases,  the popularity of the various deep learning frameworks and libraries also increase in popularity and in... Details
Neural style transfer

Neural Style Transfer

Here's a great tutorial that uses deep learning to compose one image in the style of another image. If you've ever wished that you could... Details
Top Deep Learning Interview Questions You Must Know

Top Deep Learning Interview Questions You Must Know

Data Scientist was the hottest job title of the last few years. Recently, a new challenger has risen to top of the heap: Machine Learning... Details
Advanced Keras — Constructing Complex Custom Losses and Metrics

Advanced Keras: Constructing Complex Custom Losses and Metrics

Here's an interesting article on creating and using custom loss functions in Keras. Why would you need to do this? Here's one example from the... Details
Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization

Deep Learning in IVF

Here's an interesting article in Nature about the use of AI in evaluating embryos with AI -- another use of computer vision in the medical... Details
The Top 10 AI and Deep Learning Reads of 2019 So Far

The Top 10 AI and Deep Learning Reads of 2019 So Far

The cherry blossoms are outin full force here in DC and winter is coming to an end (at least in the Northern Hemisphere).  Here's a... Details
DeepSqueak: How AI Could Decode Animal Speech

DeepSqueak: How AI Could Decode Animal Speech

Verge Science explores how AI can help decode animal communication by using rats. Why rats? Rats are social and chatty critters, but most of their... Details

Fraud Detection Using a Neural Autoencoder

Fraud detection, a common use of AI, belongs to a more general class of problems — anomaly detection. An anomaly is a generic, not domain-specific,... Details
Google open-sources GPipe, a library for efficiently training large deep neural networks

Google Open-Sources Library for Efficiently Training Large Deep Neural Nets

Last last week, Google’s AI research division open-sourced GPipe, a library for “efficiently” training deep neural networks under Lingvo, a TensorFlow framework for sequence modeling.... Details
Really Quick Questions with an Nvidia Researcher

Really Quick Questions with an Nvidia Researcher

In this video, Siraj Raval asks a series of questions of Bryan Catanzaro, the Vice President of Applied Deep Learning Research at NVIDIA. Details