Deep Learning Weekly Issue #108
Facebook F8, Google I/O, new CV and NLP datasets, PyTorch 1.1, and more...
|May 8, 2019|
We’ve also found new datasets spanning famous landmarks and text, a practical guidebook to building human-centered AI products, a larger version of GPT-2, and some new tools for PyTorch from Facebook.
As always happy reading and hacking. If you have something you think should be in next week's issue, find us on Twitter: @dl_weekly.
Until next week!
Last week at Facebook’s F8 conference, AI featured heavily in the company’s strategy to understand the content uploaded to its platform so it can surface the best content to users and remove the worst.
The latest release of PyTorch brings TensorBoard support, JIT support, and more.
Microsoft created a new interface for Azure’s automated machine learning tool that brings a drag-and-drop visual interface to users. Is this the final form of Lobe.ai, the visual deep learning platform Microsoft purchased last year?
Once again, AI featured heavily at Google’s I/O conference. Android got a number of new capabilities including full automatic speech recognition to caption videos and transcribe audio in real-time and new vision features in Lens to understand and extract information from scenes.
MIT/MGH's image-based deep learning model can predict breast cancer up to five years in advance.
Fantastic explanation of transformer networks with great visualizations.
Neat method for turning any image into a QR code.
A guidebook to help you build human-centered AI products. It’ll enable you to avoid common mistakes, design excellent experiences, and focus on people as you build AI-driven applications.
An extensive, searchable list of CV data.
“An open source effort to reproduce OpenAI’s WebText dataset. 38GB of text data from 8,013,769 documents.”
“A completely new, even larger landmark recognition dataset that includes over 5 million images (2x that of the first release) of more than 200 thousand different landmarks (an increase of 7x)”
Libraries & Code
Alibi is an open source Python library aimed at machine learning model inspection and interpretation. The initial focus on the library is on black-box, instance based model explanations.
OpenAI has decided to release a larger version of it’s GPT-2 model. The largest version has been provided to a select group of people to determine adverse impacts of release.
“Ax is an accessible, general-purpose platform for understanding, managing, deploying, and automating adaptive experiments. BoTorch, built on PyTorch, is a flexible, modern library for Bayesian optimization, a probabilistic method for data-efficient global optimization.”
An Instagram filter with AI-generated poetry.
Papers & Publications
Abstract: “....In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter. Our key contribution is a novel bidirectional shape matching framework to establish an effective glyph-style mapping at various deformation levels without paired ground truth. Based on this idea, we propose a scale-controllable module to empower a single network to continuously characterize the multi-scale shape features of the style image and transfer these features to the target text….”
Abstract: “....In this paper, we introduce NeuronBlocks, a deep neural network toolkit for natural language processing tasks. In NeuronBlocks, a suite of neural network layers are encapsulated as building blocks, which can easily be used to build complicated deep neural network models by configuring a simple JSON file. NeuronBlocks empowers engineers to build and train various NLP models in seconds even without a single line of code…”