• The Mathematics of 2048: Optimal Play with Markov Decision Processes
  In this post, we’ll use a mathematical framework called a Markov Decision Process to find provably optimal strategies for 2048 when played on the 2x2 and 3x3 boards, and also on the 4x4 board up to the 64 tile...

• Differentiable Plasticity: A New Method for Learning to Learn
  To give our artificial agents similar abilities, Uber AI Labs has developed a new method called differentiable plasticity that lets us train the behavior of plastic connections through gradient descent so that they can help previously-trained networks adapt to future conditions...

• 70% Engineering Estimates
  I just made a prediction training targeted at engineers and data scientists. The idea is to train people in the same way engineers and scientists train machine learning systems: by having them predict known outcomes of interest. The goal is to improve people's ability to make judgement based predictions about impact and cost (when little data is available)...

 
Join the Premier Machine Learning Conference

Since 2009, Predictive Analytics World, Las Vegas – June 3-7, 2018, is the leading cross-vendor conference covering the commercial deployment of machine learning, deep learning and predictive analytics. Featuring five parallel events on Business, Financial, Healthcare, Manufacturing, and Deep Learning across seven tracks, 150+ International Speakers, 150+ cutting edge sessions, 11 workshops, Mega-PAW has something for everyone. Connect in-person with leading experts and hear data scientists from companies such as Uber, Google, Caterpillar, Dell, Microsoft, State Street, Capital One, Northern Trust, Turner, Comcast, Shell, Verizon, Monsanto and many more.
10% discount for DSW readers using code DSW10 when registering.

   

---

• Deep Learning for Radars
  Radars have a long story. They used to be large, expensive and available for military only. Nowadays, many cars have a bunch of single-chip radars embedded into bumpers to enable autonomous emergency braking, cross-traffic alerts or lane change assist...

• Generative Adversarial Networks for Extreme Learned Image Compression
  Our method allows for selectively preserving some regions while fully synthesizing the rest of the image (keeping the semantics in tact)...

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
  A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enabling realistic responses to perturbations and environmental variation. We show that well-known reinforcement learning (RL) methods can be adapted to learn robust control policies capable of imitating a broad range of example motion clips, while also learning complex recoveries, adapting to changes in morphology, and accomplishing user-specified goals...

• Automated Canary Analysis at Netflix with Kayenta
  Today, in partnership with Google, we have open sourced Kayenta, a platform for Automated Canary Analysis (ACA)...

• Transforming data with zeros
  I’m currently working with a hydrologist and he raised a question that occurs quite frequently with real data — what do you do when the data look like they need a log transformation, but there are zero values?...

• Using AWS DeepLens to translate American Sign Language to speech
  ASLens uses AWS DeepLens to capture video of a person signing in American Sign Language (ASL). Then it runs a deep learning model (built with Amazon SageMaker) against each frame. When a letter from the ASL alphabet is recognised, AWS DeepLens plays the audio of that letter (using an MP3 file generated using Amazon Polly). ASLens runs locally on the AWS DeepLens, so an internet connection is not required, eliminating bandwidth issues and increasing speed....

• Delhi NCTs Best Restaurants — Visualizations of Zomato Listings
  Delhi — the capital of India, the butt of ridicule from Mumbaikars and recently crowned the Food Capital of India. So, how good are these restaurants?...

• Scientific Python in the Browser
  An early report on getting the scientific Python stack compiled to WebAssembly...

• Calculate The Biased Standard Deviation Of All Elements In A PyTorch Tensor
  Learn how to calculate the biased standard deviation of all elements in a PyTorch Tensor by using the PyTorch std operation, via a screencast video and full tutorial transcript...

• How to Design Better ML Systems with ML Canvas
  In this article, I’ll describe each block of the Machine Learning Canvas with examples and practical tips from our data scientists...

• Why React needed yet another animation library. Introducing: react-spring
  One day it struck me that the time i have been putting into working around animation related troubles could perhaps be spent bringing them together, befriending them so to say. That day react-spring was born...

• Data Science from Scratch: First Principles with Python "It does three things superbly: covers the basic low level tools of a data scientist (the "from scratch" part), gives a great overview of useful Python programming examples for those new to Python, and gives an amazingly succinct yet high level overview of the mathematics and statistics required for data science..."...
  For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page...