AI Weekly 24 Nov 2017

Hi, last week in AI industry brought us great papers about autonomous driving from Apple, big AI survey and 2 significant resources, which you can use to your own projects! Enjoy your weekend reading other news and don’t forget to share it with your friends ;)

Btw. if you want to be always on time with AI weekly, feel free to follow it on fb:


Fantastic GANs and where to find them II — This is the follow-up blog post of the original Fantastic GANs and where to find them. If you haven’t checked that article or you are completely new to GANs, consider giving it a quick read — there’s a brief summary of the previous post ahead, though. It has been 8 months since the last post and GANs aren’t exactly known for being a field with few publications.

A Survey of Artificial General Intelligence Projects for Ethics, Risk, and Policy — Artificial general intelligence (AGI) is AI that can reason across a wide range of domains. It has long been considered the “grand dream” or “holy grail” of AI. It also poses major issues of ethics, risk, and policy due to its potential to transform society: if AGI is built, it could either help solve the world’s problems or cause major catastrophe, possibly even human extinction. This paper presents the first-ever survey of active AGI R&D projects in terms of ethics, risk, and policy.


Introducing TensorFlow Feature Columns — Part 2 of a blog series that introduces TensorFlow Datasets and Estimators. This article is all about feature columns — a data structure describing the features that an Estimator requires for training and inference. As you’ll see, feature columns are very rich, enabling you to represent a diverse range of data.

Deep Learning Toolkit for Medical Image Analysis — DLTK is a neural networks toolkit written in python, on top of TensorFlow. It is developed to enable fast prototyping with a low entry threshold and ensure reproducibility in image analysis applications, with a particular focus on medical imaging. Its goal is to provide the community with state of the art methods and models and to accelerate research in this exciting field.


Open Images ( ) has been updated to V3: Now with a total of 4.5M bounding-box annotations covering 600 diverse object classes.

Reinforcement Learning: An Introduction Second edition, (in progress, Complete Draft).

Gender recognition and biometric identification using a large dataset of hand images — 11k Hands dataset, a collection of 11,076 hand images (1600 x 1200 pixels) of 190 subjects, of varying ages between 18–75 years old. Each subject was asked to open and close his fingers of the right and left hands. Each hand was photographed from both dorsal and palmar sides with a uniform white background and placed approximately in the same distance from the camera.


Capsule Networks (CapsNets) — Tutorial

Machine Learning with Google Cloud and Intel® IoT Gateway Technology


VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection — Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird’s eye view projection.

Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and Authentication — This paper proposes a computational approach for analysis of strokes in line drawings by artists. Authors aim at developing an AI methodology that facilitates attribution of drawings of unknown authors in a way that is not easy to be deceived by forged art. The methodology used is based on quantifying the characteristics of individual strokes in drawings.

High-fidelity speech synthesis with WaveNet — this paper introduces details of the new model and the “probability density distillation” technique deepmind team developed to allow the system to work in a massively parallel computing environment.

Understanding Medical Conversations — Good documentation helps create good clinical care by communicating a doctor’s thinking, their concerns, and their plans to the rest of the team. Unfortunately, physicians routinely spend more time doing documentation than doing what they love most — caring for patients. Doctors often spend ~6 hours in an 11-hour workday in the Electronic Health Records (EHR) on documentation. Consequently, one study found that more than half of surveyed doctors report at least one symptom of burnout.