Mads Kalør

CTO @ - ML Engineer

[Towards Data Science @TDataScience]

Digging Into My Year of Spotify Streaming with Track Embeddings by @mKaloer https://t.co/lqZUr4BsFl

[Mads Kalør @mKaloer]

@SpotifyPlatform Hi, just FYI, the selection on your mobile site for your web APi does not always show the correct content (see screenshot)

[Mads Kalør @mKaloer]

I just published TFServingCache: A Distributed LRU-Cache for Serving TensorFlow Models in Kubernetes https://t.co/unJcYmOtqj #TensorFlow #MachineLearning

[Eric Topol @EricTopol]

Taking a bathroom break from #COVID19
to go to the smart toilet, which uses deep learning #AI to analyze all of one's excrements 💩
https://t.co/bFKmf2P47O @natBME @StanfordMed @StanfordEng

[AK @_akhaliq]

CookGAN: Meal Image Synthesis from Ingredients
pdf: https://t.co/T63W7JVxEj
abs: https://t.co/8TI8WY80rL

[Mads Kalør @mKaloer]

@fulhack I made an app at university that did theft detection based on the owner's gait using HMMs of the accelerometer data. Worked so well that our supervisor thought we were cheating!

[François Chollet @fchollet]

TensorFlow 2.0.0 release is out now: https://t.co/s9tudRs6Kn

Huge milestone for the machine learning ecosystem. Congratulations to the hundreds (yes) of people who have contributed!

[Andrew Ng @AndrewYNg]

Introducing The Batch, a new weekly newsletter from @deeplearningai_! AI is growing so fast that it’s hard to know what news is useful or valuable. Subscribe to The Batch for a curated report on the latest AI research and industry-shaping events: https://t.co/UtwpmsIPub

[Mads Kalør @mKaloer]

Early detection of sepsis utilizing deep learning on electronic health record event sequences - ideas from my Master's thesis enhanced by health scientists
https://t.co/3CL6OZa4ch

[DeepLearning.AI @DeepLearningAI]

Should all layers be initialized the same, or is it important to change the initialization for different types of layers (e.g. LSTM weights vs CNN weights)? Read the new AI Notes tutorial on initialization and let us know your thoughts in the comments: https://t.co/HugvG16Prc

[Yann LeCun @ylecun]

Deep learning needs more theory.

Many workshops I have helped organize in the last decade (e.g. at IPAM) have attempted to bring ML/DL folks together with mathematicians and... https://t.co/jvOH36lYH8

[Mads Kalør @mKaloer]

@rasmusbergpalm Congrats Rasmus!

[Andrew Ng @AndrewYNg]

Chatted about my journey through AI, including stories from early days of Google Brain & Coursera, plus Landing AI and https://t.co/Ryb1M2QyNn. Hope you'll find useful ideas and inspiration from this. Thanks @kevin_scott for doing this! https://t.co/dleWKkGYEA

[Gizmodo @Gizmodo]

IBM Watson reportedly recommended cancer treatments that were "unsafe and incorrect"
https://t.co/7WdwdFDLvz

[Jure Leskovec @jure]

Can we predict side effects of drug combinations? Our paper gains insights on how different drug combinations interacted with protein networks to create side effects -- before they happen. https://t.co/7kAsX7JFLn
https://t.co/pPCthSQ0dj

[Andrej Karpathy @karpathy]

most common neural net mistakes: 1) you didn't try to overfit a single batch first. 2) you forgot to toggle train/eval mode for the net. 3) you forgot to .zero_grad() (in pytorch) before .backward(). 4) you passed softmaxed outputs to a loss that expects raw logits. ; others? :)

[Sundar Pichai @sundarpichai]

Today we’re sharing our AI principles and practices. How AI is developed and used will have a significant impact on society for many years to come. We feel a deep responsibility to get this right. https://t.co/TCatoYHN2m

[Mads Kalør @mKaloer]

Nice article about a neat trick! A fast sparse multiplication into an embedding is indeed really useful in terms of performance and effectiveness for many tasks involving categorical input features https://t.co/HIxGbDkjFb

[Rachel Thomas @math_rachel]

my new blog post: An Introduction to Deep Learning for Tabular Data https://t.co/OrYS1bUAmk

[Mark Riedl @mark_riedl]

massive, AI-powered roach breeding farm produces more than six billion cockroaches per year https://t.co/DixE8LgCkE << what could possibly go wrong?

[Shira Ovide @ShiraOvide]

Every paragraph of this terrific Palantir story is absolutely bonkers. https://t.co/qdXvWgvtwk