Bag of Tricks in Machine Learning

https://ai.googleblog.com/2019/04/evaluating-unsupervised-learning-of.html

The choice of random seed across different runs has a larger impact on disentanglement scores than the model choice and the strength of regularization (while naively one might expect that more regularization should always lead to more disentanglement). A good run with a bad hyperparameter can easily beat a bad run with a good hyperparameter. 

https://anand.typepad.com/datawocky/2008/03/more-data-usual.html

Trying intergalactic travel before learning how to walk from ProgrammerHumor

Happens everytime from ProgrammerHumor

New blog post: "A Recipe for Training Neural Networks" https://t.co/5lBy4J77aS a collection of attempted advice for training neural nets with a focus on how to structure that process over time

— Andrej Karpathy (@karpathy) April 25, 2019

NLP:

• Good-Enough Compositional Data Augmentation (Arxiv)
• Easy data augmentation techniques for boosting performance on text classification tasks (Github)

Speech

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (Arxiv)

Image

• albumentations (Github)
• fastai (doc)

• https://developer.amazon.com/blogs/alexa/
• https://ai.google/research/pubs/?area=SpeechProcessing
• https://research.fb.com/publications/?cat=8
• https://www.microsoft.com/en-us/research/blog/category/intelligence/speech-and-dialog/
• https://machinelearning.apple.com/

Next Level Thinking from ProgrammerHumor

https://github.com/fritzlabs/Awesome-Mobile-Machine-Learning/blob/master/README.md

Comment from discussion DoomChicken69’s comment from discussion "LinkedIn August Work Report: Employers Desperate for Data Scientists".

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale. from MachineLearning