AI Essentials

Research

Discover how AI, Machine Learning and advanced algorithms impact our lives, our jobs and the economy thanks to expert articles that include discussion on the potential, limits and consequences of AI

Top news of the week: 09.02.2021.

Machine learning
Learning
Neural network
Randomness
Scientific method
Delhi

Research

@thinkmariya shared
On Feb 8, 2021
We can find time series data in medicine, weather forecasting, biology, supply chain management, stock prices forecasting, etc. Here are some of the most important deep learning algorithms for time series forecasting. https://t.co/r5DaLnZnfE #AI #DeepLearning #MachineLearning
Open
Time Series Forecasting with Deep Learning and Attention Mechanism

Time Series Forecasting with Deep Learning and Attention Mechanism

An overview of the architecture and the implementation details of the most important Deep Learning algorithms for Time Series Forecasting.

@deliprao shared
On Feb 9, 2021
RT @paulnovosad: 📢📢Trying something new: Instead of waiting 10 years until our judicial bias paper publishes, we are posting the public data RIGHT AWAY. 80 million cases, 80k judges, the near universe of Indian lower court cases from 2010–2018. 🧵 1/5 Details: https://t.co/Pdm9O0zRaS
Open
Big Data for Justice

Big Data for Justice

An open-access dataset of 80 million Indian legal case records

@stanfordnlp shared
On Feb 8, 2021
RT @StanfordAILab: AI courses at @Stanford: “It’s all student demand-driven, which just reflects the huge breakthroughs that have been made in AI recently and the huge enthusiasm among students to learn this,” said Christopher Manning Ph.D. ’94 @chrmanning, director of SAIL. https://t.co/L5phH0jCA0
Open
The rise of AI in Stanford’s CS curricula

The rise of AI in Stanford’s CS curricula

During the 2010s, AI-related courses experienced large growth, both in terms of the number of courses and the number of students enrolling in these courses.

@_rockt shared
On Feb 2, 2021
Pretty cool entry point, even for RL environments. For example: https://t.co/SlIKSPaB6a https://t.co/GnJQNJiLdS
Open
NetHack Learning Environment

NetHack Learning Environment

The NetHack Learning Environment (NLE) is a Reinforcement Learning environment based on NetHack 3.6.6. It is designed to provide a standard reinforcement learning interface to the game, and ...

@MSFTResearch shared
On Feb 3, 2021
Microsoft researchers are publicly releasing Microsoft Vision Model ResNet-50, a pretrained vision model that sets state of the art by mean average score across 7 computer vision benchmarks. Learn how multi-task learning & web supervision make it possible: https://t.co/TvOGFWCLvH
Open
Microsoft Vision Model ResNet-50 combines web-scale data and multi-task learning to achieve state of the art

Microsoft Vision Model ResNet-50 combines web-scale data and multi-task learning to achieve state of the art

Microsoft researchers are publicly releasing Microsoft Vision Model ResNet-50, a pretrained vision model that sets state of the art by mean average score across 7 computer vision ...

@ericjang11 shared
On Feb 7, 2021
RT @Luke_Metz: New article about two of my favorite things: meta-learning and Jax! This explores the complex meta-loss landscapes which merge from unrolled optimization procedures and shows why gradient based hyperparameter tuning can be hard even for simple problems. https://t.co/HbcGo7hxes https://t.co/yTEd9w2Lm0
Open
Exploring hyperparameter meta-loss landscapes with Jax

Exploring hyperparameter meta-loss landscapes with Jax

An exploration into complex meta-loss landscapes with Jax.

@kchonyc shared
On Feb 8, 2021
RT @david_sontag: Attention all clinicians interested in machine learning & AI... work with MIT students! We are recruiting mentors for course projects in our Machine Learning for Healthcare Spring 2021 class. Details & sign up here: https://t.co/kjOzIOYWjK @willieboag @rayruizhiliao @ckbjimmy
Open
MIT ML4H Clinical Mentor Signup

MIT ML4H Clinical Mentor Signup

MIT course 6.871 Machine Learning for Healthcare (https://mlhcmit.github.io/) introduces students to machine learning in healthcare, including the nature of clinical data and the use of ...

@jeremyphoward shared
On Feb 3, 2021
RT @tomcocobrico: @TheZachMueller @_willfalcon @PyTorchLightnin @fastdotai @abhi1thakur "Prior to Flash, there was no customization DL framework to enable simple inference, fine-tuning, and customization of state of the art models on new data in a matter of minutes." https://t.co/NCVq22rnLB
Open
Introducing Lightning Flash — Get Started with Deep Learning in a Flash

Introducing Lightning Flash — Get Started with Deep Learning in a Flash

Flash is a collection of tasks for fast prototyping, baselining and finetuning for quick and scalable DL built on PyTorch Lightning.