Neural Networks and Deep Learning Training for computer science students.
| # | Course Name | Week Name | Notes |
|---|---|---|---|
| 01 | Neural Networks and Deep Learning | Week 01: Introduction to Deep Learning |
15 Lecture Notes 30 Practical Labs |
| Week 02: Neural Networks Basics | |||
| Week 03: Shallow Neural Networks | |||
| Week 04: Deep Neural Networks | |||
| 02 | Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization | Week 01: Practical Aspects of Deep Learning | |
| Week 02: Optimization Algorithms | |||
| Week 03: Hyperparameter Tuning, Batch Normalization and Programming Frameworks | |||
| 03 | Structuring Machine Learning Projects | Week 01: ML Strategy | |
| Week 02: ML Strategy | |||
| 04 | Convolutional Neural Networks | Week 01: Foundations of Convolutional Neural Networks | |
| Week 02: Deep Convolutional Models: Case Studies | |||
| Week 03: Object Detection | |||
| Week 04: Special Applications: Face recognition and Neural Style Transfer | |||
| 05 | Sequence Models | Week 01: Recurrent Neural Networks | |
| Week 02: Natural Language Processing and Word Embeddings | |||
| Week 03: Sequence Models and Attention Mechanism | |||
| Week 04: Transformaer Network |
| # | Course Name | Week Name | Notes |
|---|---|---|---|
| 06 | Introduction to TensorFlow for Artificial Intelligence | Week 01: A New Programming Paradigm |
15 Lecture Notes 30 Practical Labs |
| Week 02: Introduction to Computer Vision | |||
| Week 03: Enhancing Vision with Convolutional Neural Networks | |||
| Week 04: Using Real-world Images | |||
| 07 | Convolutional Neural Networks in TensorFlow | Week 01: Exploring a Larger Dataset | |
| Week 02: Augmentation: A technique to avoid overfitting | |||
| Week 03: Transfer Learning | |||
| Week 04: Multiclass Classifications | |||
| 08 | Natural Language Processing in TensorFlow | Week 01: Sentiment in text | |
| Week 02: Word Embeddings | |||
| Week 03: Sequence models | |||
| Week 04: Sequence models and literature | |||
| 09 | Sequences Time Series and Prediction | Week 01: Sequences and Prediction | |
| Week 02: Deep Neural Networks for Time Series | |||
| Week 03: Recurrent Neural Networks for Time Series | |||
| Week 04: Real-world time series data |
| # | Course Name | Week Name | Notes |
|---|---|---|---|
| 10 | Custom Models, Layers, and Loss Functions with TensorFlow | Week 01: Functional APIs |
15 Lecture Notes 30 Practical Labs |
| Week 02: Custom Loss Functions | |||
| Week 03: Custom Layers | |||
| Week 04: Custom Models | |||
| Week 05: Bonus Content - Callbacks | |||
| 11 | Custom and Distributed Training with TensorFlow | Week 01: Differentiation and Gradients | |
| Week 02: Custom Training | |||
| Week 03: Graph Mode | |||
| Week 04: Distributed Training | |||
| 12 | Advanced Computer Vision with TensorFlow | Week 01: Introduction to Computer Vision | |
| Week 02: Object Detection | |||
| Week 03: Image Segmentation | |||
| Week 04: Visualization and Interpretability | |||
| 13 | Generative Deep Learning with TensorFlow | Week 01: Style Transfer | |
| Week 02: AutoEncoders | |||
| Week 03: Variational AutoEncoders | |||
| Week 04: GANs |
