2021 DS/ML digest 01

2021 DS/ML digest 01

Posted by snakers41 on February 1, 2021

Audio / Speech

Another standalone VAD - https://github.com/amsehili/auditok
Amazon echo flex teardown - https://electronupdate.blogspot.com/2020/12/amazon-echo-flex-teardown.html
RETHINKING EVALUATION IN ASR: ARE OUR MODELS ROBUST ENOUGH? - http://arxiv.org/abs/2010.11745

Tech / Internet

Ben Evans’ presentations - https://www.ben-evans.com/presentations
How amazon is run internally - https://digitstodollars.com/2021/01/18/how-does-amazon-do-it/
Online speech and publishing - https://www.ben-evans.com/benedictevans/2021/1/17/speech-and-publishing
Excel now has lambda functions - https://www.microsoft.com/en-us/research/blog/lambda-the-ultimatae-excel-worksheet-function/

ML

DALL·E: Creating Images from Text - https://openai.com/blog/dall-e/
Proper Scoring Rules - https://dyakonov.org/2020/12/28/proper-scoring-rules/
When BERT Plays The Lottery, All Tickets Are Winning - https://thegradient.pub/when-bert-plays-the-lottery-all-tickets-are-winning/
Deformable Neural Radiance Fields - https://nerfies.github.io/
Recognizing Pose Similarity in Images and Videos - https://ai.googleblog.com/2021/01/recognizing-pose-similarity-in-images.html
Interfaces for Explaining Transformer Language Models - https://jalammar.github.io/explaining-transformers/
Animations of Gradient Descent and Loss Landscapes of Neural Networks in Python - https://towardsdatascience.com/animations-of-gradient-descent-and-loss-landscapes-of-neural-networks-in-python-e757f3584057
A Step by Step Backpropagation Example - https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/
SEFR: A Fast Linear-Time Classifier for Ultra-Low Power Devices - https://arxiv.org/pdf/2006.04620.pdf
A Visual History of Interpretation for Image Recognition - https://thegradient.pub/a-visual-history-of-interpretation-for-image-recognition/
Microsoft DeBERTa surpasses human performance on the SuperGLUE benchmark - https://www.microsoft.com/en-us/research/blog/microsoft-deberta-surpasses-human-performance-on-the-superglue-benchmark/
A Corrected CBOW Implementation - http://arxiv.org/abs/2012.15332
Controllable Neural Text Generation - https://lilianweng.github.io/lil-log/2021/01/02/controllable-neural-text-generation.html
Three mysteries in deep learning: Ensemble, knowledge distillation, and self-distillation - https://www.microsoft.com/en-us/research/blog/three-mysteries-in-deep-learning-ensemble-knowledge-distillation-and-self-distillation/
Analysis of 100 Weeks of Curated AI News - https://www.skynettoday.com/digests/ai-news-analysis
High-Low Frequency Detectors - https://distill.pub/2020/circuits/frequency-edges/
Stabilizing Live Speech Translation in Google Translate - https://ai.googleblog.com/2021/01/stabilizing-live-speech-translation-in.html
Improving Mobile App Accessibility with Icon Detection - https://ai.googleblog.com/2021/01/improving-mobile-app-accessibility-with.html
Can AI Let Justice Be Done? - https://thegradient.pub/robot-judges/

Admin

Building Docker Images The Proper Way - https://martinheinz.dev/blog/42
Canonical has a light-weight VM for Ubuntu - https://multipass.run/
The SEFR classifier (Scalable, Efficient, and Fast classifieR) - https://machinethink.net/blog/sefr-classifier-in-swift/
Dockerfile security best practices - https://habr.com/ru/company/swordfish_security/blog/537280/
WSL 1 vs WSL 2 - https://habr.com/ru/company/vdsina/blog/535214/

Code

Preventing Software Rot - https://software.rajivprab.com/2020/04/25/preventing-software-rot/
The Simple Ways to Refactor Terrible Code - https://martinheinz.dev/blog/40
Scheduling All Kinds of Recurring Jobs with Python - https://martinheinz.dev/blog/39