Visualizing Weights

distill.pub 1h

We present techniques for visualizing, contextualizing, and understanding neural network weights.

Machine Learning for Computer Architecture

feedproxy.google.com 7h

Posted by Amir Yazdanbakhsh, Research Scientist, Google Research One of the key contributors to recent machine learning (ML) advancements...

---

Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning

feedproxy.google.com 1d

Posted by Mohammad Babaeizadeh, Research Engineer and Dumitru Erhan, Research Scientist, Google Research Model-free reinforcement learnin...

---

Curve Circuits

distill.pub 3d

Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch.

#157 - Natalya Bailey: Rocket Engines and Electric Spacecraft Propulsion

lexfridman.com 3d

Natalya Bailey is a rocket propulsion engineer from MIT and now CTO of Accion Systems. Please support this podcast by checking out our sponsors: – Munk Pack: and use code LEX to get 20% off – Four Sigmatic: and use code LexPod to get up to 60% off – Blinkist: and use code LEX to get 25%...

---

Do you have a non-paywalled version?

medium.com 4d

---

Not sure if you realize that this article is behind a paywall (I can't see it)

medium.com 6d

Learning to Reason Over Tables from Less Data

feedproxy.google.com 6d

Posted by Julian Eisenschlos AI Resident, Google Research, Zürich The task of recognizing textual entailment , also known as natural lan...

---

Improving Mobile App Accessibility with Icon Detection

feedproxy.google.com 7d

Posted by Gilles Baechler and Srinivas Sunkara, Software Engineers, Google Research Voice Access enables users to control their Android ...

---

Addressing Range Anxiety with Smart Electric Vehicle Routing

feedproxy.google.com 8d

Posted by Kostas Kollias and Sreenivas Gollapudi, Research Scientists, Geo Algorithms Team, Google Research Mapping algorithms used for n...

Your ML ad here

you.com soon

Call for papers? New API? Kaggle competition? Open position? Now you can advertise opportunities relevant to machine learning here. Ping [email protected]

High/Low frequency detectors

distill.pub 8d

A family of early-vision filters reacting to contrasts between spatial gratings of different frequency

---

Stabilizing Live Speech Translation in Google Translate

feedproxy.google.com 9d

Posted by Naveen Arivazhagan, Senior Software Engineer and Colin Cherry, Staff Research Scientist, Google Research The transcription fea...

---

Scaling Kubernetes to 7,500 Nodes

openai.com 10d

We've scaled Kubernetes clusters to 7,500 nodes, producing a scalable infrastructure for large models like GPT-3, CLIP, and DALL·E, but also for rapid small-scale iterative research such as Scaling Laws for Neural Language Models. Scaling a single Kubernetes cluster to this size is rarely done and requires some

---

Improving Indian Language Transliterations in Google Maps

feedproxy.google.com 13d

Posted by Cibu Johny, Software Engineer, Google Research and Saumya Dalal, Product Manager, Google Geo Nearly 75% of India’s population —...

---

RxR: A Multilingual Benchmark for Navigation Instruction Following

feedproxy.google.com 14d

Posted by Alexander Ku, Software Engineer and Peter Anderson, Research Scientist, Google Research A core challenge in machine learning (M...

---

ToTTo: A Controlled Table-to-Text Generation Dataset

feedproxy.google.com 20d

Posted by Ankur Parikh and Xuezhi Wang, Research Scientists, Google Research In the last few years, research in natural language generati...

---

Recognizing Pose Similarity in Images and Videos

feedproxy.google.com 21d

Posted by Jennifer J. Sun, Student Researcher and Ting Liu, Senior Software Engineer, Google Research Everyday actions, such as jogging, ...

---

Google Research: Looking Back at 2020, and Forward to 2021

feedproxy.google.com 23d

Posted by Jeff Dean, Senior Fellow and SVP of Google Research and Health, on behalf of the entire Google Research community When I joined...

---

Hybrid chips can run AI on battery-powered devices

news.stanford.edu 24d

In traditional electronics, separate chips process and store data, wasting energy as they toss data back and forth over what engineers call a “memory wall.” New algorithms combine several energy-efficient hybrid chips to create the illusion of one mega–AI chip.

---

DALL·E: Creating Images from Text

openai.com on 5 January

We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.

CLIP: Connecting Text and Images

openai.com on 5 January

We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision.

Your ML ad here

you.com soon

Call for papers? New API? Kaggle competition? Open position? Now you can advertise opportunities relevant to machine learning here. Ping [email protected]

---

Organizational Update from OpenAI

openai.com on 29 December

It’s been a year of dramatic change and growth at OpenAI. In May, we introduced GPT-3—the most powerful language model to date—and soon afterward launched our first commercial product, an API to safely access artificial intelligence models using simple, natural-language prompts. We’re proud of these and

---

#149 - Diana Walsh Pasulka: Aliens, Technology, Religion, and the Nature of Belief

lexfridman.com on 28 December

Diana Walsh Pasulka is a professor of philosophy and religion at UNCW and author of American Cosmic: UFOs, Religion, and Technology. Please support this podcast by checking out our sponsors: – LMNT: to get free shipping – Grammarly: to get 20% off premium – Business Wars: – Cash App: and use code LexPodcast to get $10...

---

#148 - Charles Isbell and Michael Littman: Machine Learning and Education

lexfridman.com on 26 December

Charles Isbell is the Dean of the College of Computing at Georgia Tech. Michael Littman is a computer scientist at Brown University. Please support this podcast by checking out our sponsors: – Athletic Greens: and use code LEX to get 1 month of fish oil – Eight Sleep: and use code LEX to get special savings – MasterClass:...

Blue People v. City of Ney

ai.stanford.edu on 26 December

The official Stanford AI Lab blog

---

Better Language Models and Their Implications

openai.com on 22 December

We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization.

---

End-to-End, Transferable Deep RL for Graph Optimization

feedproxy.google.com on 17 December

Posted by Yanqi Zhou and Sudip Roy, Research Scientists, Google Research An increasing number of applications are driven by large and co...

My heartfelt apology

animakumar.wpcomstaging.com on 17 December

I want to wholeheartedly apologize to everyone hurt by my words. I want to assure you that I bear no animosity. I want to be part of an inclusive community where all voices are heard.  I am so…

---

My departure from Twitter

animakumar.wpcomstaging.com on 16 December

Many of you are very concerned about why my Twitter account is no longer active. I have voluntarily decided to de-activate my account in the interest of my safety and to reduce anxiety for my loved…

---

Privacy Considerations in Large Language Models

feedproxy.google.com on 15 December

Posted by Nicholas Carlini, Research Scientist, Google Research Machine learning-based language models trained to predict the next word i...

---

Pain and Machine Learning

blog.shakirm.com on 12 December

Was so excited to get this opportunity to talk about pain and learning at the NeurIPS2020 Workshop on Biological and Artificial RL. This is the text of the talk.:film_frames:Watch the video h…

---

Portrait Light: Enhancing Portrait Lighting with Machine Learning

feedproxy.google.com on 11 December

Posted by Yun-Ta Tsai 1 and Rohit Pandey, Software Engineers, Google Research Professional portrait photographers are able to create com...

Your ML ad here

you.com soon

Call for papers? New API? Kaggle competition? Open position? Now you can advertise opportunities relevant to machine learning here. Ping [email protected]

Through the Eyes of Birds and Frogs: Writing and Surveys in Machine Learning Research

blog.shakirm.com on 11 December

Savoured the opportunity to talk about writing surveys and reviews at the NeurIPS2020 Workshop on ML Retrospectives, Surveys & Meta-Analyses (ML-RSA) This is the text of the talk. :film_frames:Watc…

---

MediaPipe Holistic — Simultaneous Face, Hand and Pose Prediction, on Device

feedproxy.google.com on 10 December

Posted by Ivan Grishchenko and Valentin Bazarevsky, Research Engineers, Google Research Real-time, simultaneous perception of human pose...

---

A Model-Based Approach Towards Identifying the Brain’s Learning Algorithms

ai.stanford.edu on 9 December

Introduction

Naturally Occurring Equivariance in Neural Networks

distill.pub on 8 December

Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.

Studying trust in autonomous products

news.stanford.edu on 8 December

Stanford engineers investigated how people’s moods might affect their trust of autonomous products, such as smart speakers. They uncovered a complicated relationship.

iGibson: A Simulation Environment to Train AI Agents in Large Realistic Scenes

ai.stanford.edu on 8 December

Why simulation for AI?

---

Offline Reinforcement Learning: How Conservative Algorithms Can Enable New Applications

bair.berkeley.edu on 7 December

The BAIR Blog

Google at NeurIPS 2020

feedproxy.google.com on 7 December

Posted by Jaqui Herman and Cat Armato, Program Managers This week marks the beginning of the 34 th annual Conference on Neural Informatio...

Stanford AI Lab Papers and Talks at NeurIPS 2020

ai.stanford.edu on 7 December

The official Stanford AI Lab blog

---

Using AutoML for Time Series Forecasting

feedproxy.google.com on 4 December

Posted by Chen Liang and Yifeng Lu, Software Engineers, Google Research, Brain Team Time series forecasting is an important research are...

---

Transformers for Image Recognition at Scale

feedproxy.google.com on 3 December

Posted by Neil Houlsby and Dirk Weissenborn, Research Scientists, Google Research While convolutional neural networks (CNNs) have been u...

Your ML ad here

you.com soon

Call for papers? New API? Kaggle competition? Open position? Now you can advertise opportunities relevant to machine learning here. Ping [email protected]

---

Can implicit regularization in deep learning be explained by norms?

offconvex.github.io on 27 November

Algorithms off the convex path.

---

Navigating Recorder Transcripts Easily, with Smart Scrolling

feedproxy.google.com on 24 November

Posted by Itay Inbar, Senior Software Engineer, Google Research Last year we launched Recorder , a new kind of recording app that made au...

---

Learning from Language Explanations

ai.stanford.edu on 23 November

Imagine you’re a machine learning practitioner and you want to solve some classification problem, like classifying groups of colored squares as being either 1s or 0s. Here’s what you would typically do: collect a large dataset of examples, label the data, and train a classifier:

---

The Language Interpretability Tool (LIT): Interactive Exploration and Analysis of NLP Models

feedproxy.google.com on 20 November

Posted by James Wexler, Software Developer and Ian Tenney, Software Engineer, Google Research As natural language processing (NLP) models...

#140 - Lisa Feldman Barrett: Love, Evolution, and the Human Brain

lexfridman.com on 20 November

Lisa Feldman Barrett is a neuroscientist, psychologist, and author. Please support this podcast by checking out our sponsors: – Athletic Greens: and use code LEX to get 1 month of fish oil – Eight Sleep: and use code LEX to get $200 off – MasterClass: to get 15% off annual sub – BetterHelp: to get 10%...

Learning State Abstractions for Long-Horizon Planning

bair.berkeley.edu on 20 November

The BAIR Blog

---

Haptics with Input: Using Linear Resonant Actuators for Sensing

feedproxy.google.com on 18 November

Posted by Artem Dementyev, Hardware Engineer, Google Research As wearables and handheld devices decrease in size, haptics become an incr...