• Mapping The AI toolchain
  Access to AI will be democratized. During this transition, we believe AI – particularly deep learning – will begin to resemble a general-purpose computing platform. But a new set of tools will be necessary to make that vision a reality. To advance the conversation, we are publishing an alpha landscape of the emerging AI Toolchain...

• Arbitrary Image Stylization in the Browser
  This is an implementation of an arbitrary image stylization algorithm running purely in the browser using TensorFlow.js. As with all neural style transfer algorithms, a neural network attempts to "draw" one picture, the Content (usually a photograph), in the style of another, the Style (usually a painting)...

• Automated testing in the modern data warehouse
  If data issues have lasting consequences, why are we less sophisticated at testing than our software developing counterparts?...

 
Master the essential data science skills. Get the job. This weekend, at 50% off

If you’re looking for a program that pulls together all essential data science trainings, check out the 365 Data Science program. Get your Python, SQL, Statistics, Mathematics, Machine and Deep learning training from an instructor team that has worked together to bring you a seamless data science education. Build up on each newly acquired skill with the next logical one and talk to your instructors if you need help!
The 365 Data Science program is developed with the end goal of getting the job even if you don’t have any prior knowledge!
Save 50% on your yearly subscription by using the code 8L4CK_FR1D4Y.
View curriculum.

• Discovery of independently controllable features through autonomous goal setting
  Despite recent breakthroughs in artificial intelligence, machine learning agents remain limited to tasks predefined by human engineers. The autonomous and simultaneous discovery and learning of many-tasks in an open world remains very challenging for reinforcement learning algorithms. In this blog post we explore recent advances in developmental learning to tackle the problems of autonomous exploration and learning...

• Machine learning, meet quantum computing
  A quantum version of the building block behind neural networks could be exponentially more powerful...

• Punctuation as Native Language Interference
  In this paper, we describe experiments designed to explore and evaluate the impact of punctuation marks on the task of native language identification....

• Animations with receiver operating characteristic curve (ROC curve)
  I made a new animation to demonstrate how an ROC curve relates to sensitivity and specificity for all possible cutoffs...

• DeepMasterPrints:
  Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution
  In this work we generate complete image-level MasterPrints known as DeepMasterPrints, whose attack accuracy is found to be much superior than that of previous methods...

• Rethinking ImageNet Pre-training
  We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization....

• CheXNeXt: Deep learning for chest radiograph diagnosis
  We developed CheXNeXt, a deep learning algorithm to concurrently detect 14 clinically important diseases in chest radiographs...

• A Convergence Theory for Deep Learning via Over-Parameterization
  In this work, we prove why simple algorithms such as stochastic gradient descent (SGD) can find global minima on the training objective of DNNs. We only make two assumptions: the inputs do not degenerate and the network is over-parameterized ... solving one of the most important unsolved problems in DNN ...

• Flatten A PyTorch Tensor
  Learn how to flatten a PyTorch Tensor by using the PyTorch view operation, via a screencast video and full tutorial transcript...

• PySyft Step-By-Step Tutorial
  In this step-by-step tutorial series, you'll learn about all the ways PySyft can be used to bring Privacy and Decentralization to the Deep Learning ecosystem. This tutorial series is continually updated with new features as they are implemented, and is designed for complete beginners...

• sPyNNaker: A Software Package for Running PyNN Simulations on SpiNNaker
  How to program a million-core SpiNNaker machine...

• Data Smart: Using Data Science to Transform Information into Insight
  "The best single book on Data Science today. I handle the data analysis and BI for the delivery side of a huge internet-based retail company, and have been a fan of Foreman's since his "Analytics Made Skeezy" blog days. His explanations are clear, his examples are to the point, and throughout it all, he is results-oriented."...
  
  For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page