Receive the Data Science Weekly Newsletter every Thursday
Easy to unsubscribe at any time. Your e-mail address is safe.
Data Science Weekly Newsletter
April 25, 2019
A Recipe for Training Neural Networks
Some few weeks ago I posted a tweet on “the most common neural net mistakes”, listing a few common gotchas related to training neural nets. The tweet got quite a bit more engagement than I anticipated (including a webinar :)). Clearly, a lot of people have personally encountered the large gap between “here is how a convolutional layer works” and “our convnet achieves state of the art results”. So I thought it could be fun to brush off my dusty blog to expand my tweet to the long form that this topic deserves...
We’ve created Musenet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles...
In a recent post , Derwen’s Paco Nathan reveals themes for the upcoming Rev Summit and previews what he is most excited for at the conference.
Come to New York City on May 23–24 to learn from data science teams and leaders at Netflix, Slack, Stitch Fix, Domino Data Lab, Microsoft, Dell, Red Hat, Google, Turner Broadcasting System, Humana, Workday, Lloyds Banking Group, BNP Paribas Cardif, and many others about topics like:
How to develop a mature, sustainable data science practice with tangible impact on the business.
Specific steps the world’s leading model-driven organizations took to elevate data science internally.
Best practices, methodologies, and technologies for amplifying collaboration across teams.
How Artificial Intelligence Is Changing Science
The latest AI algorithms are probing the evolution of galaxies, calculating quantum wave functions, discovering new chemical compounds and more. Is there anything that scientists do that can’t be automated?...
How to hide from the AI surveillance state with a color printout
AI-powered video technology is becoming ubiquitous, tracking our faces and bodies through stores, offices, and public spaces. In some countries the technology constitutes a powerful new layer of policing and government surveillance. Fortunately, as some researchers from the Belgian university KU Leuven have just shown, you can often hide from an AI video system with the aid of a simple color printout...
Evaluating the Unsupervised Learning of Disentangled Representations
In "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations" (to appear at ICML 2019), we perform a large-scale evaluation on recent unsupervised disentanglement methods, challenging some common assumptions in order to suggest several improvements to future work on disentanglement learning. This evaluation is the result of training more than 12,000 models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets...
Intelligible speech synthesis from neural decoding of spoken sentences
Decoding speech from neural activity is challenging because speaking requires extremely precise and dynamic control of multiple vocal tract articulators on the order of milliseconds. Here, we designed a neural decoder that explicitly leverages the continuous kinematic and sound representations encoded in cortical activity5,6 to generate fluent and intelligible speech. A recurrent neural network first decoded vocal tract physiological signals from direct cortical recordings, and then transformed them to acoustic speech output...
Free-form Video Inpainting with 3D Gated Convolution & Temporal
In this paper, we introduce a deep learning based free-form video inpainting model, with proposed 3D gated convolutions to tackle the uncertainty of free-form masks and a novel Temporal PatchGAN loss to enhance temporal consistency. In addition, we collect videos and design a free-form mask generation algorithm to build the free-form video inpainting (FVI) dataset for training and evaluation of video inpainting models. We demonstrate the benefits of these components and experiments on both the FaceForensics and our FVI dataset suggest that our method is superior to existing ones...
Vue.ai raises $17 million for AI-driven retail products
Vue.ai, which in three years has experienced 200 percent annual revenue growth and seen household names like Macy’s, Levi’s, Diesel, Thredup, Tata, and Mercadolibre join its customer base, offers a suite of seven products designed to automate management and merchandising processes and personalize omnichannel customer experiences. In an internal study, the company claims that online shoppers spent upwards of 72 minutes on websites where its software was deployed, compared with 25 minutes on sites without it...
Tranzact is a fast paced, entrepreneurial company offering a well-rounded suite of marketing solutions to help insurance companies stay ahead of the competition. The Data Scientist will be solving the toughest problems at Tranzact by using data. More specifically, responsible for gathering data, conducting analysis, building predictive algorithms and communicating findings to drive profitable growth and performance across Tranzact. Must have a strong grasp on the data structure, business needs, and statistical and predictive modeling...