Deep Learning & Neural Networks with Python

Course Summary

Learn the fundamentals of Deep Learning applications by building, training and deploying PyTorch models from scratch. You’ll work with transfer learning using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) as well as learn how to deploy your models.

28 Sections · 304 Pages · By Michael Frantz

  • Level

    Advanced to Professional

  • Duration

    225 Hours. Or, ~3 months of dedicated learning @ 15-20 hours per week

  • What's included

    157 lessons. 94 videos. 100+ functional examples. 36 exercises. 2-3 portfolio projects.

  • Certificate

    Deep Learning & Neural Networks Certificate

Unlock this course

$12/month Core Membership

7-day free trial

Unlock all courses

$29/month Pro Membership

7-day free trial

This course is part of the following career track:

  1. 1) Introduction

    1. About the Deep Learning Course
      14 min
    2. Deep Learning Course Setup
      4 min
    3. What is Deep Learning
      10 min
    4. Feedback: Introduction
    5. Feedback: Introduction

  2. 2) Fundamentals: Linear Regression with Torch

    1. Introduction to Neural Networks
      3 min
    2. Video: Introduction to Neural Networks
      1 min
    3. Linear Regression with Torch
    4. Single-variable Linear Regression with Torch
      7 min
    5. Video: Single Variable Linear Regression
      5 min
    6. Video: Linear Regression Refresher
      5 min
    7. Video: Mean Squared Error (MSE)
      3 min
    8. Video Solution: Exercise 2.1 Visualize Your Data
      2 min
    9. Mean Squared Error (MSE) Loss Function
      7 min
    10. Video: scikit-learn Walkthrough
      2 min
    11. Sklearn Linear Regression
      4 min
    12. Pytorch Linear Regression
      7 min
    13. Video: Pytorch Linear Regression
      8 min
    14. What is Gradient Descent
      5 min
    15. Link: DS/ML Gradient Descent
    16. Quiz: Linear Regression with Torch
    17. Training Models with PyTorch
    18. Train Your First Torch Model
      15 min
    19. Video Solution: Exercise 2.5 Train Your Model
      1 min
    20. Multi Variate Linear Regression
      22 min
    21. Video: Multi Variate Linear Regression
      10 min
    22. PyTorch Linear Layer
      10 min
    23. Non Linearities and Activation Functions
      5 min
    24. Video: Non Linearities and Activation Functions
      3 min
    25. Quiz: Training Models with PyTorch
    26. Deep Neural Networks
    27. Create a Deep Neural Network
      15 min
    28. Video: Create a Deep Neural Network
      8 min
    29. Feedback: Linear Regression with Torch
    30. Feedback: Linear Regression with Torch

  3. 3) Fundamentals: Tensors and Tensor Operations

    1. Introduction: Pytorch Tensor
      3 min
    2. Video Introduction: Pytorch Tensor
      1 min
    3. What is a Tensor
      12 min
    4. Video: What is a Tensor
      5 min
    5. Quiz: Intro to Tensors
    6. Tensor Operations
    7. Tensor Scalar Operations
      5 min
    8. Video: Tensor Scalar Operations
      1 min
    9. Tensor Element Wise Operations
      6 min
    10. Video: Tensor Element Wise Operations
      1 min
    11. Broadcasting with Pytorch
      6 min
    12. Quiz: Tensor Operations
    13. Tensor Multiplication
    14. Vector Multiplication: The Dot Product of Two Vectors
      4 min
    15. Video: Vector Multiplication and Dot Product of Two Vectors
      2 min
    16. Matrix Multiplication
      5 min
    17. Video: Matrix Multiplication
      5 min
    18. Quiz: Tensor Multiplication
    19. Additional Tensor Functions
    20. Useful Tensor Functions and Methods
      3 min
    21. Torch Reshape Methods
      7 min
    22. Create Custom Sigmoid and Softmax Functions
      4 min
    23. Video: Create Custom Sigmoid and Softmax Functions
      3 min
    24. Quiz: Additional Tensor Functions
    25. Feedback: Tensors and Tensor Operations
    26. Feedback: Tensors and Tensor Operations

  4. 4) Fundamentals: Torch Data API

    1. Getting Started with the PyTorch Data API
      4 min
    2. Video: Pytorch Data API
      1 min
    3. Datasets and DataFrames
    4. Python Pandas: Create DataFrame In-Memory
      7 min
    5. Create a PyTorch Dataset
      5 min
    6. Video: Creating Pytorch Datasets
      4 min
    7. Quiz: Torch Data API
    8. Dataloader
    9. PyTorch DataLoader
      15 min
    10. Video: PyTorch Dataloaders
      6 min
    11. Out-of-Memory Data: Create a fastai Image Dataset
      8 min
    12. Video: Working with OOM Datasets
      3 min
    13. CIFAR-10 Dataset & Utility Functions
      6 min
    14. Video: Image Loading Dataset & Utility Functions
      4 min
    15. PyTorch DataSet to DataLoader using collate_fn
      10 min
    16. Video: DataSet to DataLoader with Collate Function
      5 min
    17. Quiz: Torch Data API Dataloader
    18. Feedback: Torch Data API
    19. Feedback: PyTorch Data API

  5. 5) Fundamentals: Loss Functions

    1. Loss Functions
      5 min
    2. Video: Intro to Loss Functions
      1 min
    3. Regression: Mean Squared Error
      8 min
    4. Video: Revisiting Mean Squared Error (MSE)
      3 min
    5. Quiz: Loss Functions
    6. Classification
    7. Classification: Cross Entropy Loss
      17 min
    8. Video: Cross Entropy Loss
      8 min
    9. Binary Classification: Binary Cross Entropy
      6 min
    10. Video: Binary Cross Entropy
      3 min
    11. Multi-class Classification
      5 min
    12. Video: Multi-class Classification
      2 min
    13. Quiz: Classification
    14. Feedback
    15. Feedback: Loss Functions

  6. 6) Fundamentals: Optimizers

    1. Introduction to ML Optimizers
      4 min
    2. Video: Intro to ML Optimizers
      1 min
    3. Create a Bivariate Dataset
      5 min
    4. Create a Small Neural Network
      8 min
    5. Video: Exercise 6.1 & 6.2 Solution
      3 min
    6. Quiz: Intro to Optimizers
    7. Stochastic Gradient Descent
    8. Stochastic Gradient Descent (SGD)
      6 min
    9. Video: Stochastic Gradient Descent (SGD)
      2 min
    10. SGD with Momentum
      7 min
    11. Video: SGD with Momentum
      3 min
    12. Quiz: Stochastic Gradient Descent
    13. RMSProp and Adam
    14. RMSProp Optimizer
      7 min
    15. Video: RMSProp Optimizer
      4 min
    16. Adam Optimizer
      6 min
    17. Video: Adam Optimizer
      6 min
    18. Quiz: RMSProp & Adam
    19. Feedback
    20. Feedback: Optimizers

  7. 7) Fundamentals: How Models Learn

    1. Introduction: How Machine Learning Models Learn
      3 min
    2. Video: Intoduction to How Models Learn
      1 min
    3. The Derivative
    4. Definition of Derivative
      5 min
    5. Video: Revisiting Derivatives
      4 min
    6. Example of the Chain Rule Derivative
      9 min
    7. Video: The Chain Rule & Torch Backprop
      6 min
    8. Gradient: Partial Derivative
      5 min
    9. Video: From Derivative to Gradient
      3 min
    10. Exploding Gradient and Vanishing Gradient Problem
      3 min
    11. Video: Problems with Training Neural Networks
      2 min
    12. Improved Parameter Initialization
      3 min
    13. Video: Improved Parameter Initialization
      2 min
    14. Quiz: The Derivative
    15. Parameters and Batches
    16. ReLU Activation Function
      8 min
    17. Video: Non-Saturating Activation Functions
      4 min
    18. Batch Normalization
      7 min
    19. Video: Batch Normalization
      5 min
    20. Quiz: Parameters & Batches
    21. Feedback
    22. Feedback: How Models Learn

  8. 8) Fundamentals: Introduction to Classification

    1. Introduction to Classification
      5 min
    2. Video: Introduction to Classification
      1 min
    3. Video: GPU Setup
      1 min
    4. Explore Images with Matplotlib imshow
      11 min
    5. Video: Explore Images with Matplotlib imshow
      6 min
    6. Quiz: Intro to Classification
    7. Classifier Model
    8. Build a Classification Model
      7 min
    9. Video: Build a Classification Model
      7 min
    10. How to Train a Classification Model
      4 min
    11. Train Your Classification Model
      6 min
    12. Classification Model Evaluation
      8 min
    13. Video: Train and Evaluate a Classification Model
      12 min
    14. Quiz: Classifier Model
    15. Feedback
    16. Feedback: Introduction to Classification

  9. 9) Introduction to High-Level Libraries

    1. Introduction: Pytorch Lightning and FastAi
      5 min
    2. Video: Introduction to Pytorch Lightning and FastAi
      2 min
    3. MNIST Dataset
    4. MNIST Dataset Library
      5 min
    5. Video: MNIST Dataset Library
      1 min
    6. MNIST Data Cleaning
      7 min
    7. Video Solution: MNIST Data Cleaning
      1 min
    8. Load and Save Dataset
      3 min
    9. Quiz: MNIST Dataset
    10. PyTorch Lightning
    11. What is Pytorch Lightning
      3 min
    12. Launch Tensorboard in Google Colab
      3 min
    13. Video: Introduction to Pytorch Lightning
      1 min
    14. Pytorch Lightning: DataModule
      3 min
    15. Pytorch Lightning: LightningModule
      5 min
    16. Pytorch Lightning: Logging and Callback Functions
      3 min
    17. Pytorch Lightning: Trainer
      6 min
    18. ML Model Inference and Checkpoint
      8 min
    19. Quiz: PyTorch Lightning
    20. Fastai
    21. What is Fastai
      3 min
    22. Video: What is Fastai
      2 min
    23. Fastai DataLoaders
      10 min
    24. Fastai Learner
      10 min
    25. Quiz: Fastai
    26. Feedback
    27. Feedback: Introduction to High-Level Libraries

  10. Mini-Project: Fundamentals

    1. Mini-Project Introduction
      3 min
    2. Video: Fundamentals Mini-Project Introduction
      5 min
    3. Mini Project Setup & Instructions
      4 min
    4. Data Selection, EDA, and Feature Engineering
      5 min
    5. Training a Non-Deep Learning Model
      3 min
    6. Training a Deep Learning Model
      3 min
    7. Fundamentals Mini Project Report
      8 min
    8. Feedback
    9. Feedback: Fundamentals Mini Project

  11. 10) Convolutional Neural Networks (CNNs)

    1. Introduction: Convolutional Neural Networks (CNNs)
      3 min
    2. CNNs for Edge Detection
      12 min
    3. CNN: Reflective and Zero Padding
      5 min
    4. CNN: Strided Convolution
      3 min
    5. Multi-Channel Convolutional Filter
      6 min
    6. The Pytorch Conv2d Layer
      3 min
    7. Average and Max Pooling
      7 min
    8. Quiz: Convolutional Neural Networks
    9. Feedback
    10. Feedback: Introduction to Convolutional Neural Networks (CNNs)

  12. 11) Build a CNN Image Classifier

    1. Introduction: Build a Convolutional Neural Network
      3 min
    2. Video: Image Classification with CNNs
      1 min
    3. Data Cleaning
    4. Fastai: MNIST Dataset Cleaning
      6 min
    5. Video: Fastai MNIST Dataset Cleaning
      2 min
    6. CNN Model
    7. Convolutional Neural Network Tutorial
      7 min
    8. Video: Convolutional Neural Network Tutorial
      3 min
    9. Convolutional Neural Network Training
      7 min
    10. Video: Convolutional Neural Network Training
      3 min
    11. Examine Feature Map of CNN Layers
      6 min
    12. Video: What is Your Model Learning?
      3 min
    13. Quiz: Build a CNN Image Classifier
    14. Feedback
    15. Feedback: Our First Convolutional Neural Network (CNN) Image Classifier

  13. 12) Transfer Learning and ResNet

    1. Introduction: Transfer Learning
      3 min
    2. Video: ResNet and Transfer Learning
      6 min
    3. Data Cleaning
    4. Pets Data Cleaning
      6 min
    5. ResNet
    6. What is ResNet
      8 min
    7. Video: What is ResNet
      4 min
    8. ResNet Image Classification
      5 min
    9. Video: ResNet Image Classification
      1 min
    10. Quiz: ResNet
    11. Transfer Learning
    12. Transfer Learning: ResNet Pre-trained with ImageNet
      13 min
    13. Video: Transfer Learning with ResNet and ImageNet
      6 min
    14. Serve Models with GradIO
      7 min
    15. Video: Serve Models with GradIO
      3 min
    16. Build the Residual Block from Scratch (Optional)
      16 min
    17. Quiz: Transfer Learning
    18. Feedback
    19. Feedback: Transfer Learning and ResNet

  14. 13) Image Classification: Augmentation

    1. Introduction: Image Augmentation
      4 min
    2. Video: Introduction to Image Augmentation
      1 min
    3. Albumentations
    4. Image Augmentation with Albumentations
      3 min
    5. Video: Image Augmentation with Albumentations
      1 min
    6. Torchvision
    7. Image Augmentation with Torchvision
      3 min
    8. Video: Image Augmentation with Torchvision
      1 min
    9. Fastai
    10. Image Augmentation with Fastai
      3 min
    11. Video: Image Augmentation with Fastai
      3 min
    12. Experiment: Is Image Augmentation Worth It?
      10 min
    13. Feedback
    14. Feedback: Augmentation

  15. Mini-Project: Image Classification

    1. Mini-Project Introduction
      3 min
    2. Video: Mini-Project Introduction
      3 min
    3. Project Setup & Instructions
      3 min
    4. Mixup Data Augmentation Technique
      6 min
    5. Mini Project Report
      3 min
    6. Feedback
    7. Feedback: Image Classification Mini-Project

  16. 14) Data Prep for NLP with RNNs

    1. Introduction: NLP in Deep Learning
      4 min
    2. Video: Intro Data Prep for NLP
      1 min
    3. Traditional Approaches
    4. Traditional NLP with Count Vectorizer
      6 min
    5. Video: Traditional Text Prep for ML
      3 min
    6. Normalization
    7. NLP Normalization
      6 min
    8. Video: Text Normalization
      1 min
    9. Tokenization
    10. NLP Tokenization
      3 min
    11. Video: NLP Tokenization
      1 min
    12. Create a Tokenizer
      7 min
    13. Video: Create a Tokenizer
      3 min
    14. Tokenizer Examples
      11 min
    15. Video: Tokenizer Examples
      3 min
    16. Feedback
    17. Feedback: Data Preparation for NLP

  17. 15) NLP with Recurrent Neural Networks

    1. Introduction: Recurrent Neural Networks (RNN)
      4 min
    2. Tokenizer Data Cleaning
      3 min
    3. Video: Text Classification with RNNs (Intro & Setup)
      2 min
    4. Word Embeddings
    5. Word Embedding and Word Vectors
      15 min
    6. Video: Embeddings, Word Vectors and Identifying Bias
      5 min
    7. Recurrent Neural Networks
    8. Introduction to Recurrent Neural Networks (RNNs)
      3 min
    9. Video: Understanding Vanilla RNNs
      10 min
    10. Quiz: What is an RNN
    11. Problems with RNNs
      4 min
    12. Journal: RNN Problems
    13. Create a Recurrent Neural Network
      14 min
    14. Video: Problems with RNNs (and Solutions!)
      2 min
    15. LSTM and GRU
    16. GRU & LSTM Solutions for RNNs
      3 min
    17. Gated Recurrent Unit (GRU)
      8 min
    18. Long Short Term Memory (LSTM)
      6 min
    19. Text Classification
    20. NLP with RNNs for Text Classification
      15 min
    21. Video: Training an Emotion Classifier with RNNs
      7 min
    22. Feedback
    23. Feedback: Introduction to Recurrent Neural Networks

  18. 16) NLP with RNNs: Deep Dive - RNNs from Scratch

    1. Introduction: Create RNNs from Scratch
      6 min
    2. Create a RNN from Scratch Tutorial
      13 min
    3. Video: RNNs from Scratch
      1 min
    4. Problems and Solutions
    5. Problems with Vanilla RNNs
      3 min
    6. Gated Recurrent Unit Networks (GRUs)
      10 min
    7. Long Short-Term Memory (LSTM) Networks
      12 min
    8. Feedback
    9. Feedback: Deep Dive - RNNs from Scratch

  19. 17) NLP with RNNs: Pre-Training and Transfer Learning for RNNs

    1. Introduction: Pre-Training and Transfer Learning with RNNs
      6 min
    2. Video: Pre-Training and Transfer Learning with RNNs
      3 min
    3. Language Modeling
    4. NLP Dataloaders
      13 min
    5. Video: Language Modeling Data
      3 min
    6. Build with Pre-Trained Language Model
      8 min
    7. Video: Language Modeling
      2 min
    8. Transfer Learning
    9. NLP Transfer Learning
      27 min
    10. Video: Transfer Learning with RNNs
      3 min
    11. Sanity Checks
    12. Transfer Learning vs Model from Scratch
      7 min
    13. Video: Transfer Learning vs Model from Scratch
      3 min
    14. Feedback
    15. Feedback: Pre-Training and Transfer Learning for RNNs

  20. 18) Continue your NLP Learning Journey

    1. Continue Learning NLP
      3 min
    2. Video: Next Steps with NLP
      2 min

  21. Mini-Project: NLP with RNNs

    1. Introduction: NLP with RNN Mini-Project
      3 min
    2. Video: Introduction Miniproject 3
      2 min
    3. Project Setup & Instructions
      3 min
    4. NLP with RNNs Project Report
      3 min
    5. Feedback
    6. Feedback: NLP with RNNs Mini-Project

  22. 19) Introduction to Production

    1. Introduction: Production Environment
      3 min
    2. Video: Introduction to Production
      1 min
    3. Interfaces
    4. Offline and Online Inference
      9 min
    5. Feedback
    6. Feedback: Introduction to Production

  23. 20) Production: Batch Interface Lab

    1. Introduction: Batch Inference
      3 min
    2. Crontab Example
      17 min
    3. Video: Offline Batch Inference
      5 min
    4. Additional Job Scheduling Resources
      3 min
    5. Feedback
    6. Feedback: Batch Inference Lab

  24. 21) Production: Serving with a User Interface

    1. Introduction: GradIO User Interface
      3 min
    2. GradIO: Create Predict Function
      5 min
    3. Create GradIO User Interface
      5 min
    4. Video: Create GradIO User Interface
      6 min
    5. Feedback
    6. Feedback: Serving with a User Interface

  25. 22) Production: Building an Online Inference Service

    1. Introduction: Online Interfaces
      3 min
    2. Video: Introduction to Online Interfaces
      7 min
    3. Setup: Docker and Cog
      3 min
    4. Build and Launch App
    5. Create Cog Predictor and Config File
      6 min
    6. Launch Online Inference
      5 min
    7. Feedback
    8. Feedback: Online Inference

  26. Mini-Project: Production

    1. Production Mini Project Instructions
      3 min
    2. Video: Introduction to Miniproject #4
      1 min
    3. Feedback
    4. Feedback: Production Mini-Project

  27. Capstone Project

    1. Deep Learning Capstone Introduction
      3 min
    2. Video: Capstone Project Introduction
      4 min
    3. Problem Statement
      3 min
    4. Data Collection
      4 min
    5. Data Splitting, EDA, and Feature Engineering
      7 min
    6. ML Model Training & Selection
      5 min
    7. Production
      3 min
    8. Report
      3 min
    9. Presentation
      3 min
    10. Feedback
    11. Feedback: Capstone Project

  28. Certificate Request

    1. Request Completion Certificate