Neural Networks and Deep Learning (DeepLearning.AI, Andrew Ng)

About this course

Course 1 of Andrew Ng's Deep Learning Specialization: the foundations of neural networks, from logistic regression as a tiny network to deep networks, with vectorised implementations. Who it's for: learners who know some Python and basic maths and want a rigorous start in deep learning. These are the free, official videos of the "Neural Networks and Deep Learning (Course 1 of the Deep Learning Specialization)" playlist from the DeepLearningAI YouTube channel (youtube.com/@deeplearningai). All videos belong to DeepLearning.AI; Sikhami is not affiliated with DeepLearning.AI and simply arranges the public playlist into a course, so you can learn one lesson at a time and keep track of your progress.

What you will learn

• What deep learning is and supervised learning with neural networks • Logistic regression, the cost function and gradient descent • Computation graphs and derivatives • Vectorisation with Python and NumPy • Shallow neural networks, activation functions and random initialisation • Deep neural networks: forward and backward propagation, parameters and hyperparameters

Course content

1 section · 43 lectures · 5h 40m

1. 1. Neural Networks and Deep Learning (Course 1 of the Deep Learning Specialization)

   • Welcome (Deep Learning Specialization C1W1L01)5m
   • What is a Neural Network? (C1W1L02)7m
   • Supervised Learning with a Neural Network (C1W1L03)8m
   • Why is deep learning taking off? (C1W1L04)10m
   • About This Course (C1W1L05)2m
   • Course Resources (C1W1L06)1m
   • Binary Classification (C1W2L01)8m
   • Logistic Regression (C1W2L02)6m
   • Logistic Regression Cost Function (C1W2L03)8m
   • Gradient Descent (C1W2L04)11m
   • Derivatives (C1W2L05)7m
   • More Derivative Examples (C1W2L06)10m
   • Computation Graph (C1W2L07)3m
   • Derivatives With Computation Graphs (C1W2L08)14m
   • Logistic Regression Gradient Descent (C1W2L09)6m
   • Gradient Descent on m Examples (C1W2L10)8m
   • Vectorization (C1W2L11)8m
   • More Vectorization Examples (C1W2L12)6m
   • Vectorizing Logistic Regression (C1W2L13)7m
   • Vectorizing Logistic Regression's Gradient Computation (C1W2L14)9m
   • Broadcasting in Python (C1W2L15)11m
   • A Note on Python/Numpy Vectors (C1W2L16)6m
   • Quick Tour of Jupyter/iPython Notebooks (C1W2L17)3m
   • Explanation of Logistic Regression's Cost Function (C1W2L18)7m
   • Neural Network Overview (C1W3L01)4m
   • Neural Network Representations (C1W3L02)5m
   • Computing Neural Network Output (C1W3L03)9m
   • Vectorizing Across Multiple Examples (C1W3L04)9m
   • Explanation For Vectorized Implementation (C1W3L05)7m
   • Activation Functions (C1W3L06)10m
   • Why Non-linear Activation Functions (C1W3L07)5m
   • Derivatives Of Activation Functions (C1W3L08)7m
   • Gradient Descent For Neural Networks (C1W3L09)9m
   • Backpropagation Intuition (C1W3L10)15m
   • Random Initialization (C1W3L11)7m
   • Deep L-Layer Neural Network (C1W4L01)5m
   • Forward Propagation in a Deep Network (C1W4L02)7m
   • Getting Matrix Dimensions Right (C1W4L03)11m
   • Why Deep Representations? (C1W4L04)10m
   • Building Blocks of a Deep Neural Network (C1W4L05)8m
   • Forward and Backward Propagation (C1W4L06)10m
   • Parameters vs Hyperparameters (C1W4L07)7m
   • What does this have to do with the brain? (C1W4L08)3m