FlickList
Deep Learning
Deep Learning

Deep Learning

0.5 Sep 2017
Ended

Overview

English

Cast

Andrew Ng

Andrew Ng

Teacher

E1

What is Deep Learning?

Sep 23, 2017 10m
E2

What is a Neural Network?

Sep 23, 2017 10m
E3

Supervised Learning with Neural Networks

Sep 23, 2017 10m
E4

Drivers Behind the Rise of Deep Learning

Sep 23, 2017 10m
E5

Binary Classification in Deep Learning

Sep 23, 2017 10m
E6

Logistic Regression

Sep 23, 2017 10m
E7

Logistic Regression Cost Function

Sep 23, 2017 10m
E8

Gradient Descent

Sep 23, 2017 10m
E9

Derivatives

Sep 23, 2017 10m
E10

Derivatives Examples

Sep 23, 2017 10m
E11

Computation Graph

Sep 23, 2017 10m
E12

Derivatives with a Computation Graph

Sep 23, 2017 10m
E13

Logistic Regression Derivatives

Sep 23, 2017 10m
E14

Gradient Descent on m Training Examples

Sep 23, 2017 10m
E15

Vectorization

Sep 23, 2017 10m
E16

More Vectorization Examples

Sep 23, 2017 10m
E17

Vectorizing Logistic Regressio

Sep 23, 2017 10m
E18

Vectorizing Logistic Regression's Gradient Computation

Sep 23, 2017 10m
E19

Broadcasting in Python

Sep 23, 2017 10m
E20

Python-Numpy

Sep 23, 2017 10m
E21

Jupyter-iPython

Sep 23, 2017 10m
E22

Logistic Regression Cost Function Explanation

Sep 23, 2017 10m
E23

Neural Network Overview

Sep 23, 2017 10m
E24

Neural Network Representation

Sep 23, 2017 10m
E25

Computing a Neural Network's Output

Sep 23, 2017 10m
E26

Vectorizing Across Multiple Training Examples

Sep 23, 2017 10m
E27

Vectorized Implementation Explanation

Sep 23, 2017 10m
E28

Activation Functions

Sep 23, 2017 10m
E29

Why Non-Linear Activation Function?

Sep 23, 2017 10m
E30

Derivatives of Activation Functions

Sep 23, 2017 10m
E31

Gradient Descent for Neural Networks

Sep 23, 2017 10m
E32

BackPropagation Intuition

Sep 23, 2017 10m
E33

Random Initialization of Weights

Sep 23, 2017 10m
E34

Deep L-layer Neural Network

Sep 23, 2017 10m
E35

Forward Propagation in Deep Networks

Sep 23, 2017 10m
E36

Getting your Matrix Dimension Right

Sep 23, 2017 10m
E37

Why DEEP representation?

Sep 23, 2017 10m
E38

Building Blocks of Deep Neural Network

Sep 23, 2017 10m
E39

Forward Propagation for Layer L

Sep 23, 2017 10m
E40

Parameters vs Hyperparameters

Sep 23, 2017 10m
E41

Brain and Deep Learning

Sep 23, 2017 10m
E42

Train/Dev/Test sets

Sep 23, 2017 10m
E43

Bias/Variance

Sep 23, 2017 10m
E44

Basic "Recipe" of Machine Learning

Sep 23, 2017 10m
E45

Regularization

Sep 23, 2017 10m
E46

Why Regularization reduces Overfitting?

Sep 23, 2017 10m
E47

Dropout Regularization

Sep 23, 2017 10m
E48

Why does drop-out work?

Sep 23, 2017 10m
E49

Other Regularization Methods

Sep 23, 2017 10m
E50

Normalizing Input

Sep 23, 2017 10m
E51

Vanishing/Exploding Gradients

Sep 23, 2017 10m
E52

Weight Initialization for deep networks

Sep 23, 2017 10m
E53

Numerical Approximation of Gradients

Sep 23, 2017 10m
E54

Gradient Checking

Sep 23, 2017 10m
E55

Gradient Checking Implantation Notes

Sep 23, 2017 10m
E56

Mini Batch Gradient Descent

Sep 23, 2017 10m
E57

Understanding Mini-Batch Gradient Descent

TBA 10m
E58

Exponentially Weighted Averages

Sep 23, 2017 10m
E59

Understanding Exponentially Weighted Averages

Sep 23, 2017 10m
E60

Bias Correction in Exponentially Weighted Average

Sep 23, 2017 10m
E61

Gradient Descent with Momentum

Sep 23, 2017 10m
E62

RMSprop

Sep 23, 2017 10m
E63

Adam Optimization Algorithm

Sep 23, 2017 10m
E64

Learning Rate Decay

Sep 23, 2017 10m
E65

The Problem of Local Optima

Sep 23, 2017 10m
E66

Tunning Process

Sep 23, 2017 10m
E67

Right Scale for Hyperparameters

Sep 23, 2017 10m
E68

Hyperparameters tuning in Practice: Panda vs. Caviar

Sep 23, 2017 10m
E69

Batch Norm

Sep 23, 2017 10m
E70

Fitting Batch Norm into a Neural Network

Sep 23, 2017 10m
E71

Why Does Batch Norm Work?

Sep 23, 2017 10m
E72

Batch Norm at Test Time

Sep 23, 2017 10m
E73

Softmax Regression

Sep 23, 2017 10m
E74

Training a Softmax Classifier

Sep 23, 2017 10m
E75

Deep Learning Frameworks

Sep 23, 2017 10m
E76

TensorFlow

Sep 23, 2017 10m
E77

Why ML Strategy?

Sep 23, 2017 10m
E78

Orthogonalization

Sep 23, 2017 10m
E79

Single Number Evaluation Metric

Sep 23, 2017 10m
E80

Satisfying and Optimizing Metrics

Sep 23, 2017 10m
E81

train/dev/test distributions

Sep 23, 2017 10m
E82

Size of dev and test sets

Sep 23, 2017 10m
E83

When to change dev/test sets and metrics?

Sep 23, 2017 10m
E84

Why human-level performance?

Sep 23, 2017 10m
E85

Avoidable Bias

Sep 23, 2017 10m
E86

Understanding Human-Level Performance

Sep 23, 2017 10m
E87

Surpassing Human-Level Performance

Sep 23, 2017 10m
E88

Improving Your Model Performance

Sep 23, 2017 10m
E89

Carrying Out Error Analysis

Sep 23, 2017 10m
E90

Cleaning Up Incorrect Labeled Data

Sep 23, 2017 10m
E91

Build Your First System Quickly, Then Iterate

Sep 23, 2017 10m
E92

Training and Testing on Different Distributions

Sep 23, 2017 10m
E93

Bias and Variance with Mismatched data distributions

Sep 23, 2017 10m
E94

Addressing Data Mismatch

Sep 23, 2017 10m
E95

Transfer Learning

Sep 23, 2017 10m
E96

Multi-Task Learning

Sep 23, 2017 10m
E97

End-to-End Deep Learning

Sep 23, 2017 10m
E98

Whether to use End-to-End Learning

Sep 23, 2017 10m

Similar Shows

Discover more