|
| 1 | +# Course 2 - Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization |
| 2 | + |
| 3 | +**Info:** This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. |
| 4 | + |
| 5 | +After 3 weeks, you will: |
| 6 | +- Understand industry best-practices for building deep learning applications. |
| 7 | +- Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, |
| 8 | +- Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. |
| 9 | +- Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance |
| 10 | +- Be able to implement a neural network in TensorFlow. |
| 11 | + |
| 12 | +This is the second course of the Deep Learning Specialization. |
| 13 | + |
| 14 | +## Week 1 - Practical aspects of Deep Learning |
| 15 | + |
| 16 | +- Video: Train / Dev / Test sets |
| 17 | +- Video: Bias / Variance |
| 18 | +- Video: Basic Recipe for Machine Learning |
| 19 | +- Video: Regularization |
| 20 | +- Video: Why regularization reduces overfitting? |
| 21 | +- Video: Dropout Regularization |
| 22 | +- Video: Understanding Dropout |
| 23 | +- Video: Other regularization methods |
| 24 | +- Video: Normalizing inputs |
| 25 | +- Video: Vanishing / Exploding gradients |
| 26 | +- Video: Weight Initialization for Deep Networks |
| 27 | +- Video: Numerical approximation of gradients |
| 28 | +- Video: Gradient checking |
| 29 | +- Video: Gradient Checking Implementation Notes |
| 30 | +- Notepad: Initialization |
| 31 | +- Notepad: Regularization |
| 32 | +- Notepad: Gradient Checking |
| 33 | +- Video: Yoshua Bengio interview |
| 34 | + |
| 35 | +## Week 2 - Optimization algorithms |
| 36 | + |
| 37 | +- Video: Mini-batch gradient descent |
| 38 | +- Video: Understanding mini-batch gradient descent |
| 39 | +- Video: Exponentially weighted averages |
| 40 | +- Video: Understanding exponentially weighted averages |
| 41 | +- Video: Bias correction in exponentially weighted averages |
| 42 | +- Video: Gradient descent with momentum |
| 43 | +- Video: RMSprop |
| 44 | +- Video: Adam optimization algorithm |
| 45 | +- Video: Learning rate decay |
| 46 | +- Video: The problem of local optima |
| 47 | +- Notepad: Optimization |
| 48 | +- Video: Yuanqing Lin interview |
| 49 | + |
| 50 | +## Week 3 - Hyperparameter tuning, Batch Normalization and Programming Frameworks |
| 51 | + |
| 52 | +- Video: Tuning process |
| 53 | +- Video: Using an appropriate scale to pick hyperparameters |
| 54 | +- Video: Hyperparameters tuning in practice: Pandas vs. Caviar |
| 55 | +- Video: Normalizing activations in a network |
| 56 | +- Video: Fitting Batch Norm into a neural network |
| 57 | +- Video: Why does Batch Norm work? |
| 58 | +- Video: Batch Norm at test time |
| 59 | +- Video: Softmax Regression |
| 60 | +- Video: Training a softmax classifier |
| 61 | +- Video: Deep learning frameworks |
| 62 | +- Video: TensorFlow |
| 63 | +- Notepad: Tensorflow |
0 commit comments