Deep Learning's Most Important Ideas ๐Ÿ’ก | Machine Learning Monthly November 2020


Every month I publish a newsletter called Machine Learning Monthly, which gathers the latest, greatest and most important things happening in the field of machine learning.

And hoho… this issue was an absolute banger! What a phenomenal month on tour for the world of machine learning. Be sure to subscribe/submit your work for next month’s letter.

ML Monthly November 2020 –
Learn ML (my beginner-friendly course) –

Links mentioned:
My upcoming deep learning with TensorFlow course –
Alvaro’s guide to TorchServe –
TensorFlow for Mac –
TensorFlow Recommenders (TFRS) –
NYU Deep Learning course –
ML created art –
Deep Learning’s Most Important Ideas blog post –
Continuous delivery for ML –
Why we need DevOps for ML data –
Data Valuation using Reinforcement Learning (DVRL) –
Estimating Example Difficulty Using Variance of Gradients (VOG) –
AI camerman mistakes bald referee’s head for ball –

0:00 – Intro/hello
1:40 – My upcoming TensorFlow course
3:53 – Alvaro’s guide to TorchServe
7:10 – TensorFlow for Mac
11:25 – TensorFlow Recommenders
13:37 – Yann LeCun’s NYU Deep Learning course
16:15 – Machine learning created art
18:05 – Robot draws poetry on the beach
19:00 – Deep learning’s most import ideas by Denny Britz
25:55 – Continuous delivery for machine learning
29:40 – Why we need DevOps for ML data
33:51 – Papers: How hard is your data to model?
34:20 – ๐Ÿ“„ Data Valuation Using Reinforcement Learning
36:33 – ๐Ÿ“„ Estimating Example Difficulty Using Variance of Gradients
40:00 – AI cameraman mistakes bald referee’s head for soccer ball

Connect elsewhere:
Web –
Private newsletter –
Medium –
Twitter –
LinkedIn –



One Comment

  • Daniel Bourke
    December 5, 2020

    This month's issue was an absolute blast! Which one was your favourite?

    PS… don't forget, if you want to submit something for the next issue/video, send it my way: daniel at mrdbourke dot com with the subject "ML monthly submission" (or leave a comment below)

Write a comment