Trainings DL

Training in Deep Learning

---

Deep Learning

Suggested 6-month syllabus for a Deep Learning training workshop based on Sebastian Raschka's course notes, using Python and PyTorch, suitable for graduate students

Month 1-2: Foundations of Deep Learning

1. Introduction to Deep Learning Concepts and Applications [1]
2. Basics of Neural Networks and Activation Functions
3. Introduction to PyTorch: Tensors, Operations, and Autograd
4. Gradient Descent and Backpropagation
5. Loss Functions and Optimization Algorithms
6. Hands-on: Building and Training a Simple Neural Network

Month 3-4: Advanced Deep Learning Techniques

1. Convolutional Neural Networks (CNNs) for Image Classification
2. Transfer Learning and Fine-Tuning Pretrained Models
3. Recurrent Neural Networks (RNNs) and Sequence Modeling
4. Long Short-Term Memory (LSTM) Networks for Sequential Data
5. Generative Adversarial Networks (GANs) for Image Generation
6. Hands-on: Implementing CNNs, RNNs, and GANs using PyTorch

Month 5-6: Deep Learning Applications and Projects

1. Natural Language Processing with Deep Learning
2. Sentiment Analysis, Named Entity Recognition, and Language Generation
3. Object Detection and Localization using CNNs
4. Applying Deep Learning to Tabular Data: Regression and Classification
5. Final Project: Choose a Real-World Problem and Design a Deep Learning Solution
6. Showcase and Presentation of Final Projects

References

1. Introduction to Deep Learning
2. Machine Learning with PyTorch and Scikit-Learn
3. Introduction to Deep Learning and Generative
4. Sebastian Raschka Github
5. Dive into Deep Learning. Zhang, Aston and Lipton, Zachary C. and Li, Mu and Smola, Alexander J., Cambridge University Press (2023).

---

Created: 08/28/2023; Updated: 08/28/2023

CC BY-NC-SA 4.0

Carlos Lizárraga, Data Lab, Data Science Institute, University of Arizona, 2023.