Deep Learning Fundamentals

- Deep Learning Fundamentals
- Unit 1Intro to ML and DL
- Unit 2Using Tensors w/ PyTorch
- Unit 3Model Training in PyTorch
- Unit 3.1Using Logistic Regression for Classification
- Unit 3.2The Logistic Regression Computation Graph
- Unit 3.3Model Training with Stochastic Gradient Descent
- Unit 3.4Automatic Differentiation in PyTorch
- Unit 3.5The PyTorch API
- Unit 3.6Training a Logistic Regression Model in PyTorch
- Unit 3.7 Feature Normalization
- Unit 3 ExercisesUnit 3 Exercies

- Unit 4Training Multilayer Neural Networks Overview
- Unit 4.1Logistic Regression for Multiple Classes
- Unit 4.2Multilayer Neural Networks
- Unit 4.3Training a Multilayer Neural Network in PyTorch
- Unit 4.4Defining Efficient Data Loaders
- Unit 4.5Multilayer Neural Networks for Regression
- Unit 4.6Speeding Up Model Training Using GPUs
- Unit 4 ExercisesUnit 4 Exercises

- Unit 5Organizing Your Code with Lightning
- Unit 5.1 Organizing Your Code with Lightning
- Unit 5.2Training a Multilayer Perceptron using the Lightning Trainer
- Unit 5.3Computing Metrics Efficiently with TorchMetrics
- Unit 5.4Making Code Reproducible
- Unit 5.5Organizing Your Data Loaders with Data Modules
- Unit 5.6The Benefits of Logging Your Model Training
- Unit 5.7Evaluating and Using Models on New Data
- Unit 5.8Add Functionality with Callbacks
- Unit 5 ExercisesUnit 5 Exercises

- Unit 6Essential Deep Learning Tips & Tricks
- Unit 6.1 Model Checkpointing and Early Stopping
- Unit 6.2Learning Rates and Learning Rate Schedulers
- Unit 6.3Using More Advanced Optimization Algorithms
- Unit 6.4Choosing Activation Functions
- Unit 6.5Automating The Hyperparameter Tuning Process
- Unit 6.6Improving Convergence with Batch Normalization
- Unit 6.7Reducing Overfitting With Dropout
- Unit 6.8Debugging Deep Neural Networks
- Unit 6 ExercisesUnit 6 Exercises

- Unit 7Getting Started with Computer Vision
- Unit 7.1Working With Images
- Unit 7.2How Convolutional Neural Networks Work
- Unit 7.3Convolutional Neural Network Architectures
- Unit 7.4Training Convolutional Neural Networks
- Unit 7.5Improving Predictions with Data Augmentation
- Unit 7.6Leveraging Pretrained Models with Transfer Learning
- Unit 7.7Using Unlabeled Data with Self-Supervised
- Unit 7 ExercisesUnit 7 Exercises

- Unit 8Natural Language Processing and Large Language Models
- Unit 8.1Working with Text Data
- Unit 8.2Training A Text Classifier Baseline
- Unit 8.3Introduction to Recurrent Neural Networks
- Unit 8.4From RNNs to the Transformer Architecture
- Unit 8.5Understanding Self-Attention
- Unit 8.6Large Language Models
- Unit 8.7A Large Language Model for Classification
- Unit 8 ExercisesUnit 8 Exercises

- Unit 9Techniques for Speeding Up Model Training
- Unit 10 The Finale: Our Next Steps After AI Model Training

# Unit 1 Exercises

## Exercise 1: Add early-stopping to make the Perceptron more efficient.

In its original implementation, the perceptron completes the number of epochs specified via the `epochs`

argument:

```
def train(model, all_x, all_y, epochs):
...
```

However, this can result in executing too many unnecessarily. Modify the `train`

function in Section 4 (`4) Implementing the Perceptron`

such that it automatically stops when the perceptron classifies the training data perfectly.

Link to exercise notebook: https://github.com/Lightning-AI/dl-fundamentals/blob/main/unit01-ml-intro/exercises/1_early-stop/exercise_1_early-stop.ipynb

## Exercise 2: Initialize the model parameters with small random numbers instead of 0’s

Modify the Perceptron class in Section 4 such that it initializes the weights and bias unit using small random numbers (detailed instructions are provided in the notebook). Then observe how it affects the training performance of the perceptron. Does it train/learn better or worse?

Link to exercise notebook: https://github.com/Lightning-AI/dl-fundamentals/blob/main/unit01-ml-intro/exercises/2_random-weights/exercise_2_random-weights.ipynb

## Exercise 3: Use a learning rate for updating the weights and bias unit

Modify the `Perceptron`

class using a so-called *learning rate* for updating the weights and bias unit. The learning rate is a setting for adjusting the magnitude of the weight and bias unit updates. Changing the learning rate can accelerate or slow down the learning speed of the perceptron (in terms of the number of iterations required for finding a good decision boundary).

Link to exercise notebook: https://github.com/Lightning-AI/dl-fundamentals/blob/main/unit01-ml-intro/exercises/3_learning-rate/exercise_3_learning-rate.ipynb

**Log in or create a free Lightning.ai account to access:**

- Quizzes
- Completion badges
- Progress tracking
- Additional downloadable content
- Additional AI education resources
- Notifications when new units are released
- Free cloud computing credits

##### Watch Video 1

Unit 1 Exercises