| Name | First Aired | Runtime | Image | |
|---|---|---|---|---|
| S01E01 | What is Deep Learning? |
September 23, 2017
YouTube
|
10 | |
| S01E02 | What is a Neural Network? |
September 23, 2017
YouTube
|
10 | |
| S01E03 | Supervised Learning with Neural Networks |
September 23, 2017
YouTube
|
10 | |
| S01E04 | Drivers Behind the Rise of Deep Learning |
September 23, 2017
YouTube
|
10 | |
| S01E05 | Binary Classification in Deep Learning |
September 23, 2017
YouTube
|
10 | |
| S01E06 | Logistic Regression |
September 23, 2017
YouTube
|
10 | |
| S01E07 | Logistic Regression Cost Function |
September 23, 2017
YouTube
|
10 | |
| S01E08 | Gradient Descent |
September 23, 2017
YouTube
|
10 | |
| S01E09 | Derivatives |
September 23, 2017
YouTube
|
10 | |
| S01E10 | Derivatives Examples |
September 23, 2017
YouTube
|
10 | |
| S01E11 | Computation Graph |
September 23, 2017
YouTube
|
10 | |
| S01E12 | Derivatives with a Computation Graph |
September 23, 2017
YouTube
|
10 | |
| S01E13 | Logistic Regression Derivatives |
September 23, 2017
YouTube
|
10 | |
| S01E14 | Gradient Descent on m Training Examples |
September 23, 2017
YouTube
|
10 | |
| S01E15 | Vectorization |
September 23, 2017
YouTube
|
10 | |
| S01E16 | More Vectorization Examples |
September 23, 2017
YouTube
|
10 | |
| S01E17 | Vectorizing Logistic Regressio |
September 23, 2017
YouTube
|
10 | |
| S01E18 | Vectorizing Logistic Regression's Gradient Computation |
September 23, 2017
YouTube
|
10 | |
| S01E19 | Broadcasting in Python |
September 23, 2017
YouTube
|
10 | |
| S01E20 | Python-Numpy |
September 23, 2017
YouTube
|
10 | |
| S01E21 | Jupyter-iPython |
September 23, 2017
YouTube
|
10 | |
| S01E22 | Logistic Regression Cost Function Explanation |
September 23, 2017
YouTube
|
10 | |
| S01E23 | Neural Network Overview |
September 23, 2017
YouTube
|
10 | |
| S01E24 | Neural Network Representation |
September 23, 2017
YouTube
|
10 | |
| S01E25 | Computing a Neural Network's Output |
September 23, 2017
YouTube
|
10 | |
| S01E26 | Vectorizing Across Multiple Training Examples |
September 23, 2017
YouTube
|
10 | |
| S01E27 | Vectorized Implementation Explanation |
September 23, 2017
YouTube
|
10 | |
| S01E28 | Activation Functions |
September 23, 2017
YouTube
|
10 | |
| S01E29 | Why Non-Linear Activation Function? |
September 23, 2017
YouTube
|
10 | |
| S01E30 | Derivatives of Activation Functions |
September 23, 2017
YouTube
|
10 | |
| S01E31 | Gradient Descent for Neural Networks |
September 23, 2017
YouTube
|
10 | |
| S01E32 | BackPropagation Intuition |
September 23, 2017
YouTube
|
10 | |
| S01E33 | Random Initialization of Weights |
September 23, 2017
YouTube
|
10 | |
| S01E34 | Deep L-layer Neural Network |
September 23, 2017
YouTube
|
10 | |
| S01E35 | Forward Propagation in Deep Networks |
September 23, 2017
YouTube
|
10 | |
| S01E36 | Getting your Matrix Dimension Right |
September 23, 2017
YouTube
|
10 | |
| S01E37 | Why DEEP representation? |
September 23, 2017
YouTube
|
10 | |
| S01E38 | Building Blocks of Deep Neural Network |
September 23, 2017
YouTube
|
10 | |
| S01E39 | Forward Propagation for Layer L |
September 23, 2017
YouTube
|
10 | |
| S01E40 | Parameters vs Hyperparameters |
September 23, 2017
YouTube
|
10 | |
| S01E41 | Brain and Deep Learning |
September 23, 2017
YouTube
|
10 | |
| S01E42 | Train/Dev/Test sets |
September 23, 2017
YouTube
|
10 | |
| S01E43 | Bias/Variance |
September 23, 2017
YouTube
|
10 | |
| S01E44 | Basic "Recipe" of Machine Learning |
September 23, 2017
YouTube
|
10 | |
| S01E45 | Regularization |
September 23, 2017
YouTube
|
10 | |
| S01E46 | Why Regularization reduces Overfitting? |
September 23, 2017
YouTube
|
10 | |
| S01E47 | Dropout Regularization |
September 23, 2017
YouTube
|
10 | |
| S01E48 | Why does drop-out work? |
September 23, 2017
YouTube
|
10 | |
| S01E49 | Other Regularization Methods |
September 23, 2017
YouTube
|
10 | |
| S01E50 | Normalizing Input |
September 23, 2017
YouTube
|
10 | |
| S01E51 | Vanishing/Exploding Gradients |
September 23, 2017
YouTube
|
10 | |
| S01E52 | Weight Initialization for deep networks |
September 23, 2017
YouTube
|
10 | |
| S01E53 | Numerical Approximation of Gradients |
September 23, 2017
YouTube
|
10 | |
| S01E54 | Gradient Checking |
September 23, 2017
YouTube
|
10 | |
| S01E55 | Gradient Checking Implantation Notes |
September 23, 2017
YouTube
|
10 | |
| S01E56 | Mini Batch Gradient Descent |
September 23, 2017
YouTube
|
10 | |
| S01E57 | Understanding Mini-Batch Gradient Descent |
YouTube
|
10 | |
| S01E58 | Exponentially Weighted Averages |
September 23, 2017
YouTube
|
10 | |
| S01E59 | Understanding Exponentially Weighted Averages |
September 23, 2017
YouTube
|
10 | |
| S01E60 | Bias Correction in Exponentially Weighted Average |
September 23, 2017
YouTube
|
10 | |
| S01E61 | Gradient Descent with Momentum |
September 23, 2017
YouTube
|
10 | |
| S01E62 | RMSprop |
September 23, 2017
YouTube
|
10 | |
| S01E63 | Adam Optimization Algorithm |
September 23, 2017
YouTube
|
10 | |
| S01E64 | Learning Rate Decay |
September 23, 2017
YouTube
|
10 | |
| S01E65 | The Problem of Local Optima |
September 23, 2017
YouTube
|
10 | |
| S01E66 | Tunning Process |
September 23, 2017
YouTube
|
10 | |
| S01E67 | Right Scale for Hyperparameters |
September 23, 2017
YouTube
|
10 | |
| S01E68 | Hyperparameters tuning in Practice: Panda vs. Caviar |
September 23, 2017
YouTube
|
10 | |
| S01E69 | Batch Norm |
September 23, 2017
YouTube
|
10 | |
| S01E70 | Fitting Batch Norm into a Neural Network |
September 23, 2017
YouTube
|
10 | |
| S01E71 | Why Does Batch Norm Work? |
September 23, 2017
YouTube
|
10 | |
| S01E72 | Batch Norm at Test Time |
September 23, 2017
YouTube
|
10 | |
| S01E73 | Softmax Regression |
September 23, 2017
YouTube
|
10 | |
| S01E74 | Training a Softmax Classifier |
September 23, 2017
YouTube
|
10 | |
| S01E75 | Deep Learning Frameworks |
September 23, 2017
YouTube
|
10 | |
| S01E76 | TensorFlow |
September 23, 2017
YouTube
|
10 | |
| S01E77 | Why ML Strategy? |
September 23, 2017
YouTube
|
10 | |
| S01E78 | Orthogonalization |
September 23, 2017
YouTube
|
10 | |
| S01E79 | Single Number Evaluation Metric |
September 23, 2017
YouTube
|
10 | |
| S01E80 | Satisfying and Optimizing Metrics |
September 23, 2017
YouTube
|
10 | |
| S01E81 | train/dev/test distributions |
September 23, 2017
YouTube
|
10 | |
| S01E82 | Size of dev and test sets |
September 23, 2017
YouTube
|
10 | |
| S01E83 | When to change dev/test sets and metrics? |
September 23, 2017
YouTube
|
10 | |
| S01E84 | Why human-level performance? |
September 23, 2017
YouTube
|
10 | |
| S01E85 | Avoidable Bias |
September 23, 2017
YouTube
|
10 | |
| S01E86 | Understanding Human-Level Performance |
September 23, 2017
YouTube
|
10 | |
| S01E87 | Surpassing Human-Level Performance |
September 23, 2017
YouTube
|
10 | |
| S01E88 | Improving Your Model Performance |
September 23, 2017
YouTube
|
10 | |
| S01E89 | Carrying Out Error Analysis |
September 23, 2017
YouTube
|
10 | |
| S01E90 | Cleaning Up Incorrect Labeled Data |
September 23, 2017
YouTube
|
10 | |
| S01E91 | Build Your First System Quickly, Then Iterate |
September 23, 2017
YouTube
|
10 | |
| S01E92 | Training and Testing on Different Distributions |
September 23, 2017
YouTube
|
10 | |
| S01E93 | Bias and Variance with Mismatched data distributions |
September 23, 2017
YouTube
|
10 | |
| S01E94 | Addressing Data Mismatch |
September 23, 2017
YouTube
|
10 | |
| S01E95 | Transfer Learning |
September 23, 2017
YouTube
|
10 | |
| S01E96 | Multi-Task Learning |
September 23, 2017
YouTube
|
10 | |
| S01E97 | End-to-End Deep Learning |
September 23, 2017
YouTube
|
10 | |
| S01E98 |
Whether to use End-to-End Learning
series finale
|
September 23, 2017
YouTube
|
10 |
No artwork of this type.
No artwork of this type.
No artwork of this type.