StatQuest Neural Networks / Deep Learning: study plan and how long it takes
The StatQuest with Josh Starmer playlist is 33 videos and 10.9 hours long. Here's how long it takes at different paces, a week-by-week schedule built from the real videos, and a planner that turns it into your own daily plan.
33 videos · 10.9 hours · StatQuest with Josh Starmer
StatQuest's deep learning playlist builds up from the basics: neural network fundamentals, gradient descent, backpropagation, softmax and cross-entropy, RNNs and LSTMs, word embeddings, attention and transformers (encoder-only and decoder-only), RLHF, and coding a ChatGPT-like transformer from scratch in PyTorch.
It's one of the gentlest paths from zero to understanding transformers.
Who it's for: Beginners in deep learning who want each step explained slowly and clearly.
How long does it take?
The full playlist is 10.9 hours across 33 videos. Here's roughly how many days that is at different daily watch times and speeds, counting video time only:
| Daily time | At 1x | At 1.5x | At 2x |
|---|---|---|---|
| 30 min a day | 22 days | 15 days | 11 days |
| 1 h a day | 11 days | 8 days | 6 days |
| 2 h a day | 6 days | 4 days | 3 days |
Make your own schedule
The playlist link is already filled in. Press Plan, set how much time you have each day and your speed, and you'll get a day-by-day schedule with a finish date and a calendar file. It reads the live playlist, so new videos are included.
Week-by-week schedule
A sample plan at 1 hour a day and normal speed, using whole videos so none is split across days. That's 2 weeks in total. For a different pace, start date or speed, use the planner above.
Week 1Videos 1–20 · 5h 25m
Day 1 · 38m
- 1Happy Halloween (Neural Networks Are Not Scary)1m
- 2The Essential Main Ideas of Neural Networks19m
- 3The Chain Rule, Clearly Explained!!!18m
Day 2 · 1h
- 4Gradient Descent, Step-by-Step24m
- 5Neural Networks Pt. 2: Backpropagation Main Ideas18m
- 6Backpropagation Details Pt. 1: Optimizing 3 parameters simultaneously.19m
Day 3 · 57m
- 7Backpropagation Details Pt. 2: Going bonkers with The Chain Rule13m
- 8Neural Networks Pt. 3: ReLU In Action!!!9m
- 9Neural Networks Pt. 4: Multiple Inputs and Outputs14m
- 10Neural Networks Part 5: ArgMax and SoftMax14m
- 11The SoftMax Derivative, Step-by-Step!!!7m
Day 4 · 47m
- 12Neural Networks Part 6: Cross Entropy10m
- 13Neural Networks Part 7: Cross Entropy Derivatives and Backpropagation22m
- 14Neural Networks Part 8: Image Classification with Convolutional Neural Networks (CNNs)15m
Day 5 · 54m
- 15Recurrent Neural Networks (RNNs), Clearly Explained!!!17m
- 16Long Short-Term Memory (LSTM), Clearly Explained21m
- 17Word Embedding and Word2Vec, Clearly Explained!!!16m
Day 6 · 33m
- 18Sequence-to-Sequence (seq2seq) Encoder-Decoder Neural Networks, Clearly Explained!!!17m
- 19Attention for Neural Networks, Clearly Explained!!!16m
Day 7 · 36m
- 20Transformer Neural Networks, ChatGPT's foundation, Clearly Explained!!!36m
Week 2Videos 21–33 · 5h 27m
Day 8 · 56m
- 21Decoder-Only Transformers, ChatGPTs specific Transformer, Clearly Explained!!!37m
- 22Encoder-Only Transformers (like BERT) for RAG, Clearly Explained!!!19m
Day 9 · 49m
- 23Reinforcement Learning with Neural Networks: Essential Concepts24m
- 24Reinforcement Learning with Neural Networks: Mathematical Details25m
Day 10 · 58m
- 25Reinforcement Learning with Human Feedback (RLHF), Clearly Explained!!!18m
- 26Tensors for Neural Networks, Clearly Explained!!!10m
- 27Essential Matrix Algebra for Neural Networks, Clearly Explained!!!30m
Day 11 · 47m
- 28The matrix math behind transformer neural networks, one step at a time!!!24m
- 29The StatQuest Introduction to PyTorch23m
Day 12 · 54m
- 30Introduction to Coding Neural Networks with PyTorch and Lightning21m
- 31Long Short-Term Memory with PyTorch + Lightning33m
Day 13 · 32m
- 32Word Embedding in PyTorch + Lightning32m
Day 14 · 31m
- 33Coding a ChatGPT Like Transformer From Scratch in PyTorch31m
Tips for finishing
- Do the backpropagation videos with pen and paper; that's where the rest of the series pays off.
- Code along with the PyTorch videos at the end.