Practicum AI: Deep Learning Foundations

NOTE: This version of the notebooks uses PyTorch and PyTorch Lightning.

Please see this repository for the TensorFlow version.

Module 1: Neural Network Basics Objectives

By the end of this module, you will be able to:

1. Define a neural network.
2. Describe how a neural network works.
3. Discuss deep networks.
4. Discuss what can be done with neural networks.
5. Use a deep learning pre-trained model to classify an image.
6. Discuss Python AI Frameworks.

• 00_kernel_setup.ipynb Gets the environment set up on your system.
• 01_deep_learning_tour.ipynb

Module 2: Neural Network Advanced Objectives

By the end of this module, you will be able to:

1. Describe the basis of a neural network (neuron).
2. Identify and describe an artificial neuron (perceptron).
3. Discuss bias and weights.
4. Describe and identify activation functions.
5. Describe and simulate image processing in a small neural network.
6. Implement and train a perceptron using TensorFlow.

• 02.1_code_a_perceptron.ipynb
• 02.2_mnist_classifier.ipynb

Module 3 Optimization Algorithms and Hyperparameter Tuning Objectives

By the end of this module, you will be able to:

1. Describe the purpose and process of gradient descent.
2. Discuss the error loss function.
3. Describe optimizers.
4. Experiment with hyperparameter tuning.

• 03_bees_vs_wasps.ipynb

---

Additional Resources

Lawrence Moroney Video