Interested in learning how to build OCR models? Here's a great code example from @A_K_Nain showing a model that can break Captchas. https://t.co/dmXDCNEppI pic.twitter.com/Rh3Py2CBqp
— François Chollet (@fchollet) June 26, 2020
Interested in learning how to build OCR models? Here's a great code example from @A_K_Nain showing a model that can break Captchas. https://t.co/dmXDCNEppI pic.twitter.com/Rh3Py2CBqp
— François Chollet (@fchollet) June 26, 2020
Automate the tuning of hyperparameters with PyTorch Ignite using Bayesian Optimisation in Optuna. Learn more: https://t.co/VxOgKGxXbh
— PyTorch (@PyTorch) June 25, 2020
Nice example of #UNet + #EfficientNet using @TensorFlow 2.2 and tf.keras: https://t.co/BxSb0v0IcE pic.twitter.com/qwZPMatvTN
— 👩💻 DynamicWebPaige @ 127.0.0.1 🏠 (@DynamicWebPaige) June 24, 2020
Corrupt, sparse, irregular and ugly: Deep learning on time serieshttps://t.co/xCU6aqFgzf
— Jeremy #Masks4All Howard (@jeremyphoward) June 24, 2020
Deep Learning Based Text Classification: A Comprehensive Review: https://t.co/jvgMqUAt9T
— Denny Britz (@dennybritz) June 24, 2020
A neat survey on text classification techniques and datasets, all the way from doc2vec to BERT. pic.twitter.com/CYzToUyNKl
What I learned from looking at 200 machine learning tools: https://t.co/heO3IWlqYI
— Denny Britz (@dennybritz) June 24, 2020
Excellent writeup and career advice by @chipro with a good conclusion. If you’re a student or new graduate trying to maximize job opportunities, don’t get into fields like ML purely for the hype.
Matthews Correlation Coefficient https://t.co/eZ2bbpDzwV pic.twitter.com/PC2fYTvMWD
— Chris Albon (@chrisalbon) June 23, 2020
I looked at 200 tools for developing & deploying machine learning applications:
— Chip Huyen (@chipro) June 23, 2020
- how the market evolved over time
- the difference between ML applications that traditional software engineering applications
- open-source vs open-core business modelhttps://t.co/LmAcKADRJK
Kaggler @DavidMezzetti walks you through how to build a fully-automated data analysis pipeline on Kaggle in this 🔥 blog post || [READ] https://t.co/fwpwBRy8u0
— Kaggle (@kaggle) June 22, 2020
Categorical preprocessing layers are a new feature in Keras (available in tf-nightly & TF 2.3). They enable you to do string/int feature encoding directly as part of your model -- one-hot, multi-hot, indexing, hashing, etc. Check out this simple example: https://t.co/DLoUobJHYF
— François Chollet (@fchollet) June 22, 2020
Ever wondered what Bayesians are so excited about? Here's a walkthrough of a couple of mostly-correct examples for the newbie.https://t.co/LdMfV1l02U
— Brandon Rohrer (@_brohrer_) June 22, 2020
I think the most important thing I believe that people generally disagree with is probably that neural nets are composed of meaningful, interpretable features.
— Chris Olah (@ch402) June 18, 2020
Hoping our in depth characterization of curve detectors can help move the discussion forward: https://t.co/SeJA3279tZ pic.twitter.com/FYjPxf0MIj