Version mismatch in embedding-based retrieval is challenging, esp. on the infra side.
Small strongly labeled and large weakly labeled data is a very common situation we may run into in NLP or ASR modeling. Amazon search team used this three-stage NEEDLE Framework to take advantage of large weakly labeled data to improve NER. Their noise-aware loss function is interesting and worth taking a deep dive into. Paper link: https://www.amazon.science/publications/named-entity-recognition-with-small-strongly-labeled-and-large-weakly-labeled-data
Preparation: CNN course by Andrew Ng
ImageNet Leaderboard (read in reverse order)
I will go back to work on deep learning after writing bash for 6 months. Here is my plan to pick up deep learning.
- Deep learning (Andrew Ng): https://www.coursera.org/specializations/deep-learning
- Book (Part 2): https://www.deeplearningbook.org/
CV or NLP:
- Convolutional Neural Networks for Visual Recognition (Spring 2017): https://www.youtube.com/playlist?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv&disable_polymer=true
- CS224N: Natural Language Processing with Deep Learning | Winter 2019: https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z&disable_polymer=true
PyTorch and Tensorflow:
- Fast AI (PyTorch): https://www.youtube.com/playlist?list=PLfYUBJiXbdtSIJb-Qd3pw0cqCbkGeS0xn&disable_polymer=true
- Tensorflow: https://www.coursera.org/specializations/tensorflow-in-practice