In the News
Canada tries to turn its A.I. ideas into dollars
"Bringing A.I. home is a priority for the Canadian government, companies, universities and technologists. The goal, they say, is to build a business environment around the country’s expertise and to keep the experts its universities create in the country."
The dark secret at the heart of AI
No one really knows how the most advanced algorithms do what they do. That could be a problem.
The 2017 Big Data Landscape
Great review of the Big Data landscape by Matt Turck of Firstmark Capital, along with a comprehensive map of all the big players.
Learning
Why Momentum really works
We often think of Momentum as a means of dampening oscillations and speeding up the iterations, leading to faster convergence. But it has other interesting behavior. It allows a larger range of step-sizes to be used, and creates its own oscillations. This excellent article will give you more details and let you play with momentum through interactive visualizations.
Dropbox on creating a Modern OCR Pipeline
"We used computer vision and deep learning advances such as bi-directional Long Short Term Memory (LSTMs), Connectionist Temporal Classification (CTC), convolutional neural nets (CNNs), and more."
A peek at trends in Machine Learning
Looking at how the popularity of Deep Learning frameworks, models and optimization algorithms has evolved.
Federated Learning
Google shares a few details on its "Collaborative Machine Learning" approach where models are trained in a de-centralized manner. Could be used to collaboratively train models directly on users' smartphones without having to upload personal data.
Emotional chatting machine assesses your emotion and copies it
Chatbots have never been able to empathize. That looks set to change, thanks to a Chinese team that has built a chatbot capable of conveying specific emotions.
Software tools & code
Classifying white blood cells with Deep Learning
Interesting introduction to the way white blood cells are currently counted and how Deep Learning could help. With photos, code and data.
Implementation of a Differentiable Neural Computer
DeepMind announced last year that it had created a Differentiable Neural Computer (a sort of memory-augmented neural network). They have now open-sourced an implementation.
Unsupervised sentiment neuron
OpenAI has developed an unsupervised system which learns an "excellent representation" of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
Sonnet
DeepMind's open-source library for constructing neural networks on top of Tensorflow. The library uses an object-oriented approach, similar to Torch/NN, allowing modules to be created which define the forward pass of some computation.
Caffe 2
"Lightweight, modular, and scalable Deep Learning framework" by Facebook.
Hardware
Nvidia's Tesla P40 vs Google’s TPU
Google recently published a paper about the performance of its Tensor Processing Unit (TPU) and how it compared to Nvidia’s Kepler-based K80 GPU working in conjunction with Intel’s Haswell CPU. The TPU's deep learning results were impressive compared to the GPUs and CPUs, but Nvidia said it can top Google's TPU with some of its latest inference chips, such as the Tesla P40.
New Titan XP GPU
Nvidia unveiled its successor to the Titan X. With 12GB memory, 3,840 CUDA cores and 12 TFLOPs
About
This newsletter is a collection of AI news and resources curated by @dlissmyr. If you find it worthwhile, please forward to your friends and colleagues, or share on your favorite network!
Share on Twitter · Share on Linkedin · Share on Google+
Suggestions or comments are more than welcome, just reply to this email.
Thanks!