Deep Learning Specialization: Neural Networks and Deep Learning: study plan and how long it takes
The DeepLearningAI playlist is 43 videos and 5.7 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.
43 videos · 5.7 hours · DeepLearningAI
Course 1 of Andrew Ng's Deep Learning Specialization covers the foundations: logistic regression as a neural network, the computation graph, vectorization and broadcasting in Python, shallow neural networks, activation functions and gradient descent for neural networks, and forward and backward propagation in deep networks.
The lecture videos are short and follow the course's week-by-week structure.
Who it's for: Programmers with basic Python and some calculus who want a rigorous start in deep learning.
How long does it take?
The full playlist is 5.7 hours across 43 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 | 12 days | 8 days | 6 days |
| 1 h a day | 6 days | 4 days | 3 days |
| 2 h a day | 3 days | 2 days | 2 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 30 minutes 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 1–26 · 3h 11m
Day 1 · 21m
- 1Welcome (Deep Learning Specialization C1W1L01)6m
- 2What is a Neural Network? (C1W1L02)7m
- 3Supervised Learning with a Neural Network (C1W1L03)8m
Day 2 · 29m
- 4Why is deep learning taking off? (C1W1L04)10m
- 5About This Course (C1W1L05)2m
- 6Course Resources (C1W1L06)2m
- 7Binary Classification (C1W2L01)8m
- 8Logistic Regression (C1W2L02)6m
Day 3 · 27m
- 9Logistic Regression Cost Function (C1W2L03)8m
- 10Gradient Descent (C1W2L04)11m
- 11Derivatives (C1W2L05)7m
Day 4 · 29m
- 12More Derivative Examples (C1W2L06)10m
- 13Computation Graph (C1W2L07)4m
- 14Derivatives With Computation Graphs (C1W2L08)15m
Day 5 · 29m
- 15Logistic Regression Gradient Descent (C1W2L09)7m
- 16Gradient Descent on m Examples (C1W2L10)8m
- 17Vectorization (C1W2L11)8m
- 18More Vectorization Examples (C1W2L12)6m
Day 6 · 28m
- 19Vectorizing Logistic Regression (C1W2L13)8m
- 20Vectorizing Logistic Regression's Gradient Computation (C1W2L14)10m
- 21Broadcasting in Python (C1W2L15)11m
Day 7 · 28m
- 22A Note on Python/Numpy Vectors (C1W2L16)7m
- 23Quick Tour of Jupyter/iPython Notebooks (C1W2L17)4m
- 24Explanation of Logistic Regression's Cost Function (C1W2L18)7m
- 25Neural Network Overview (C1W3L01)4m
- 26Neural Network Representations (C1W3L02)5m
Week 2Videos 27–43 · 2h 29m
Day 8 · 27m
- 27Computing Neural Network Output (C1W3L03)10m
- 28Vectorizing Across Multiple Examples (C1W3L04)9m
- 29Explanation For Vectorized Implementation (C1W3L05)8m
Day 9 · 25m
- 30Activation Functions (C1W3L06)11m
- 31Why Non-linear Activation Functions (C1W3L07)6m
- 32Derivatives Of Activation Functions (C1W3L08)8m
Day 10 · 26m
- 33Gradient Descent For Neural Networks (C1W3L09)10m
- 34Backpropagation Intuition (C1W3L10)16m
Day 11 · 21m
- 35Random Initialization (C1W3L11)8m
- 36Deep L-Layer Neural Network (C1W4L01)6m
- 37Forward Propagation in a Deep Network (C1W4L02)7m
Day 12 · 22m
- 38Getting Matrix Dimensions Right (C1W4L03)11m
- 39Why Deep Representations? (C1W4L04)11m
Day 13 · 30m
- 40Building Blocks of a Deep Neural Network (C1W4L05)9m
- 41Forward and Backward Propagation (C1W4L06)11m
- 42Parameters vs Hyperparameters (C1W4L07)7m
- 43What does this have to do with the brain? (C1W4L08)3m
Tips for finishing
- Implement forward and backward propagation in NumPy yourself; it's the core skill of the course.
- Continue with Course 2 (Improving Deep Neural Networks), which has its own guide here.