Deep Learning and Modern NLP

on YouTube ↗01h 59m

" summary

Step‑by‑step notebooks use scikit‑learn tf‑idf and PyTorch to build a perceptron, RNN/LSTM and an encoder‑decoder seq2seq, with integer‑encoded embeddings and training loops you can run locally or on AWS GPUs. Datasets include Stanford Large Movie Reviews (50,000 examples, ~180k distinct tokens limited to 1,000 features) and R8/StackOverflow; PyTorch notebooks on GitHub show code and training. Results: perceptron ~0.80 accuracy, RNN starts ~0.74 then improves; seq2seq works but needs much more data and GPUs.

AI-written summary · about

" chapters (6)

1. 0:00Deep learning and NLP intro
2. 15:23Text classification with perceptron
3. 48:16Vectorization and RNNs
4. 1:14:36POS tagging with sequence models
5. 1:35:04Seq2seq models for translation
6. 1:52:13Building a seq2seq model

" related talks

• 01h 30mIntroduction to Deep Learning & Natural Language ProcessingRaghotham Sripadraj, Nischal HP · PyData London 2016
• 01h 40mA Deep Dive into NLP with PyTorchJeffrey Hsu, Susannah Klanecek · PyData London 2019
• 50mDeep Learning and NLP with SparkAndy Petrella · Scala Days Berlin 2016
• 54mNatural Language Processing with Deep Learning and TensorFlowBarbara Fusinska · NDC Porto 2019
• 53mTensorflow, deep learning and modern RNN architectures, without a PhDMartin Gorner · Devoxx Belgium 2017
• 45mDeep Learning and NLP with SparkMelanie Warrick, Andy Petrella · Scala Days Berlin 2016
• 31mDeep Learning Techniques for Natural Language ProcessingParis Buttfield-Addison · Developer Summit 2020
• 27mChoosing the right Deep Learning Framework: A Deep Learning ApproachNick Acosta · PyCon UK 2019