News Worth Sharing


#1

This topic is the place to share various exciting updates related to Machine Learning, Robotics and AI.

Here’s a first one (the video is in German):

The Cellular Conveyor, abbreviated Celluveyor, is a unique flexible modular conveying and positioning system. The engineers created it based on the approach of cellular conveying technology.


#2

A useful set of best practice for Machine Learning Engineering:
https://developers.google.com/machine-learning/rules-of-ml/


#3

Deep Video Portraits

The researchers present a novel approach that enables photo-realistic re-animation of portrait videos using only an input video.
While existing methods use only manipulations of facial expressions, they are the first to transfer the full 3D head position, head rotation, face expression, eye gaze, and eye blinking from a source actor to a portrait video of a target actor.

A link to the paper:
https://arxiv.org/abs/1805.11714

A link to the video:


#4

AutoAugment could be useful to extend the image data set used for training. Instead of manually rotation and flipping images, it should be possible to be possible to figure out the way how to increase both the amount and diversity of data in an existing training dataset with AutoAugment.

AutoAugment is an automatic way to design custom data augmentation policies for computer vision datasets, e.g., guiding the selection of basic image transformation operations, such as flipping an image horizontally/vertically, rotating an image, changing the colour of an image, etc.


#5

Learn about suitable datasets for TensorFlow beginners, retraining models for object recognition, advice for those interested in getting started in AI/ML, and the use of Cloud TPUs.


#6

FloydHub has released a new cloud IDE for deep learning - Workspaces based on Jupyter.

Workspaces is an interactive environment for developing and training deep learning models on FloydHub. You can run Jupyter notebooks, Python scripts, access the terminal, and much more.


#7

A handy overview of word embeddings by Sebastian Ruder.
He is a PhD student in Natural Language Processing and a research scientist at AYLIEN.


#8

A handy summary of “10 Best Robot Arms to 3D Print or Buy”. I was aware of few already, but here’s a list created by Emmett Grames just a few days ago:


#9

Recently Google has been releasing many machine learning examples of machine and Seedbank. Seedbank is a registry and search engine for Colab notebooks for and around machine learning for rapid exploration and learning.

Collection of Interactive Machine Learning Examples


#10

A brilliant overview of the current state of Word Embeddings and Sentence Embeddings by Thomas Wolf.

The Current Best of Universal Word Embeddings and Sentence Embeddings


#11

A fantastic collection of material to study reinforcement learning:


#12

Few tutorials ROS Development Studio related tutorials.