• Reinforcement Learning, Fast and Slow
  Our new paper, reviews recent techniques in deep RL that narrow the gap in learning speed between humans and agents, & demonstrate an interplay between fast and slow learning w/ parallels in animal/human cognition...

• How a Google Street View image of your house predicts risk of a car accident
  Insurance companies, banks, and health-care organizations can dramatically improve their risk models by analyzing images of policyholders’ houses, say researchers...

• Would artificial intelligence like to say something about architecture?
  Stanislas Chaillou, a Master's candidate in Architecture and Fulbright fellow at the Harvard Graduate School of Design, believes that artificial intelligence can offer in-depth analysis and alternative strategies to the design of floor plans...

Find A Data Science Job Through Vettery

Vettery specializes in tech roles and is completely free for job seekers. Interested? Submit your profile, and if accepted onto the platform, you can receive interview requests directly from top companies growing their data science teams.
Get started.

• AI researchers want to study AI the same way social scientists study humans
  Maybe we don’t need to look inside the black box after all. We just need to watch how machines behave, instead...

• Detailed Human Shape Estimation from Single Image by HMD
  This paper presents a novel framework to recover detailed human body shapes from a single image... we propose a novel learning based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information...

• A weather tech startup wants to do forecasts based on cell phone signals
  ClimaCell claims its service, which taps into millions of wireless devices, is 60% more accurate than traditional forecasting methods...

• Why managing machines is harder than you think
  Excellent slides for Strata London 2019 talk on building machine learning products by ⁦Pete Skomoroch⁩...

• "Self-Supervised Learning"
  I [Yann LeCun] now call it "self-supervised learning", because "unsupervised" is both a loaded and confusing term. In self-supervised learning, the system learns to predict part of its input from other parts of it input. In other words a portion of the input is used as a supervisory signal to a predictor fed with the remaining portion of the input...

• wav2vec: Unsupervised Pre-training for Speech Recognition
  We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task...

• Unsupervised Data Augmentation
  Data augmentation is often associated with supervised learning. We find *unsupervised* data augmentation works better. It combines well with transfer learning (e.g. BERT) and improves everything when datasets have a small number of labeled examples...

• Local Relation Networks for Image Recognition
  This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference...

The premier machine learning conference series is back!

Predictive Analytics World (PAW) brings together five co-located industry-specific events in Las Vegas: PAW Business, PAW Financial, PAW Industry 4.0, PAW Healthcare and Deep Learning World, gathering the top practitioners and the leading experts in data science and machine learning. By design, this mega-conference is where to meet the who's who and keep up on the latest techniques, making it the leading machine learning event. On stage: Google, Apple, Uber, Facebook, LinkedIn, Twitter and more...
 
Want to post here? Email us for details >> team@datascienceweekly.org

• BatchNorm2d: How to use the BatchNorm2d Module in PyTorch
  Learn how to use the PyTorch BatchNorm2d Module to accelerate Deep Network training by reducing internal covariate shift, via a screencast video and full tutorial transcript...

• The Power of Building on an Accelerating Platform: How DeepVariant Uses Intel’s AVX Optimizations
  TensorFlow CPU optimizations accelerate genomics computations in DeepVariant by >3x. Learn how in this blog from the Brain Genomics team...

• Choice of Symplectic Integrator in Hamiltonian Monte Carlo
  This is a bit of a deep dive into our choice of integrator in Hamiltonian Monte Carlo (HMC). As a spoiler alert, we find that the leapfrog integrator is empirically the fastest, or at least no slower, than other integrators. It is still interesting to consider what choice we have made, and why we have made it...

• Reproducible Research with R and R Studio
  "a very practical book that teaches good practice in organizing reproducible data analysis and comes with a series of examples..."...
  For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page
  .

   

  ---

   
  P.S., Want to reach our audience / fellow readers? Consider sponsoring - grab a spot now; first come first served! All the best, Hannah & Sebastian