Coursera
My notes / works from Coursera courses.
Contents
Introduction
This repository contains my solutions for labs and programming assignments on Coursera courses. Certain resources required by the codes may be lacking due to limitations on downloading course materials from Coursera and uploading them to GitHub. The lacking resources are mostly datasets, pre-trained models or certain weight matrices.
Courses
TensorFlow: Advanced Techniques (Specialization)
Custom Models, Layers, and Loss Functions with TensorFlow
1.Details
Week 1 - Functional APIs
- Lab: Functional API Practice
- Lab: Multi-output
- Lab: Siamese network
- Programming Assignment: Multiple Output Models using Keras Functional API
Week 2 - Custom Loss Functions
- Lab: Huber Loss lab
- Lab: Huber Loss object
- Lab: Contrastive loss in the siamese network (same as week 1's siamese network)
- Programming Assignment: Creating a custom loss function
Week 3 - Custom Layers
- Lab: Lambda layer
- Lab: Custom dense layer
- Lab: Activation in a custom layer
- Programming Assignment: Implement a Quadratic Layer
Week 4 - Custom Models
Week 5 - Bonus Content - Callbacks
Custom and Distributed Training with Tensorflow
2.Details
Week 1 - Differentiation and Gradients
Week 2 - Custom Training
- Lab: Training Basics
- Lab: Fashion MNIST using Custom Training Loop
- Programming Assignment: Breast Cancer Prediction
Week 3 - Graph Mode
Week 4 - Distributed Training
Advanced Computer Vision with TensorFlow
3.Details
Week 1 - Introduction to Computer Vision
- Lab: Transfer Learning
- Lab: Transfer Learning with ResNet 50
- Lab: Image Classification and Object Localization
- Programming Assignment: Bird Boxes
Week 2 - Object Detection
- Lab: Implement Simple Object Detection
- Lab: Predicting Bounding Boxes for Object Detection
- Programming Assignment: Zombie Detector
Week 3 - Image Segmentation
- Lab: Implement a Fully Convolutional Neural Network
- Lab: Implement a UNet
- Lab: Instance Segmentation Demo
- Programming Assignment: Image Segmentation of Handwritten Digits
Week 4 - Visualization and Interpretability
DeepLearning.AI TensorFlow Developer (Specialization)
Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
1.Details
Week 1 - A New Programming Paradigm
Week 2 - Introduction to Computer Vision
Week 3 - Enchancing Vision with Convolutional Neural Networks
Week 4 - Using Real-world Images
Convolutional Neural Networks in TensorFlow
2.Details
Week 1 - Exploring a Larger Dataset
Programming Assignment: Exercise 1 - Cats vs. Dogs
Week 2 - Augmentation: A Technique to Avoid Overfitting
Programming Assignment: Exercise 2 - Cats vs. Dogs using augmentation
Week 3 - Transfer Learning
Programming Assignment: Exercise 3 - Horses vs. humans using Transfer Learning
Week 4 - Multiclass Classifications
Programming Assignment: Exercise 4 - Multi-class classifier
Unable to download horse-or-human.zip
Natural Language Processing in TensorFlow
3.Details
Week 1 - Sentiment in Text
- Ungraded External Tool: Exercise 1 - Explore the BBC news archive
- Ungraded External Tool: Exercise 1 - Explore the BBC news archive (answer)
Week 2 - Word Embeddings
- Ungraded External Tool: Exercise 2 - BBC news archive
- Ungraded External Tool: Exercise 2 - BBC news archive (answer)
Week 3 - Sequence Models
- Ungraded External Tool: Exercise 3 - Exploring overfitting in NLP
- Ungraded External Tool: Exercise 3 - Exploring overfitting in NLP (answer)
Week 4 - Sequence Models and Literature
Sequences, Time Series and Prediction
4.Details
Week 1 - Sequences and Prediction
- Ungraded External Tool: Exercise 1 - Create and predict synthetic data
- Ungraded External Tool: Exercise 1 - Create and predict synthetic data (answer)
Week 2 - Deep Neural Networks for Time Series
- Ungraded External Tool: Exercise 2 - Predict with a DNN
- Ungraded External Tool: Exercise 2 - Predict with a DNN (answer)
Week 3 - Recurrent Neural Networks for Time Series
- Ungraded External Tool: Exercise 3 - Mean Absolute Error
- Ungraded External Tool: Exercise 3 - Mean Absolute Error (answer)
Week 4 - Real-world Time Series Data
Generative Adversarial Networks (GANs) (Specialization)
Build Basic Generative Adversarial Networks (GANs)
1.Details
Week 1 - Intro to GANs
Week 2 - Deep Convolutional GANs
Week 3 - Wasserstein GANs with Gradient Penalty
Week 4 - Conditional GAN & Controllable Generation
Build Better Generative Adversarial Networks (GANs)
2.Details
Week 1 - Evaluation of GANs
Unable to download inception_v3_google-1a9a5a14.pth
, fid_images_tensor.npz
Week 2 - GAN Disadvantages and Bias
Week 3 - StyleGAN and Advancements
Apply Generative Adversarial Networks (GANs)
3.Details
Week 1 - GANs for Data Augmentation and Privacy
Week 2 - Image-to-Image Translation with Pix2Pix
Unable to download pix2pix_15000.pth
, maps
Week 3 - Unpaired Translation with CycleGAN
Unable to download horse2zebra
, cycleGAN_100000.pth
Natural Language Processing (Specialization)
Natural Language Processing with Classification and Vector Spaces
1.Details
Week 1 - Sentiment Analysis with Logistic Regression
- Lab: Natural Language preprocessing
- Lab: Visualizing word frequencies
- Lab: Visualizing tweets and Logistic Regression models
- Programming Assignment: Assignment: Logistic Regression
Week 2 - Sentiment Analysis with Naive Bayes
- Lab: Visualizing likelihoods and confidence ellipses
- Programming Assignment: Assignment: Naive Bayes
Week 3 - Vector Space Models
- Lab: Linear algebra in Python with Numpy
- Lab: Manipulating word embeddings
- Lab: Another explanation about PCA
- Programming Assignment: Assignment: Word Embeddings
Week 4 - Machine Translation and Document Search
Natural Language Processing with Probabilistic Models
2.Details
Week 1 - Autocorrect
Week 2 - Part of Speech Tagging and Hidden Markov Models
- Lab: Working with text data: numpy
- Lab: Working with text data: string tags
- Programming Assignment: Part of Speech Tagging
Week 3 - Autocomplete and Language Models
- Lab: Corpus preprocessing for N-grams
- Lab: Building the language model
- Lab: Language model generalization
- Programming Assignment: Autocomplete
Week 4 - Word Embeddings with Neural Networks
Natural Language Processing with Sequence Models
3.Details
Week 1 - Neural Netowrks for Sentiment Analysis
- Lab: Introduction to Trax
- Lab: Classes and Subclasses
- Lab: Data Generators
- Programming Assignment: Sentiment with Deep Neural Networks
Week 2 - Recurrent Neural Networks for Language Modelling
- Lab: Hidden State Activation
- Lab: Working with JAX NumPy and Calculating Perplexity
- Lab: Vanilla RNNs, GRUs and the scan function
- Lab: Creating a GRU model using Trax
- Programming Assignment: Deep N-grams
Week 3 - LSTMs and Named Entity Recognition
Week 4 - Siamese Networks
Natural Language Processing with Attention Models
4.Details
Week 1 - Neural Machine Translation
Week 2 - Text Summarization
Week 3 - Question Answering
Week 4 - Chatbot
Deep Learning (Specialization)
Neural Networks and Deep Learning
1.Details
Week 1 - Introduction to Deep Learning
- No labs / programming assignments
Week 2 - Neural Network Basics
- Practice Programming Assignment: Python Basics with numpy (optional)
- Programming Assignment: Logistic Regression with a Neural Network mindset
Week 3 - Shallow Neural Networks
Week 4 - Deep Neural Networks
Improving Deep Neural Networks Hyperparameter tuning, Regularization and Optimization
2.Details
Week 1 - Practical Aspects of Deep Learning
- Programming Assignment: Initialization
- Programming Assignment: Regularization
- Programming Assignment: Gradient Checking
Week 2 - Optimization Algorithms
Week 3 - Hyperparameter Tuning, Batch Normalization and Programming Frameworks
Structuring Machine Learning Projects
3.Details
- No labs / programming assignments
Convolutional Neural Networks
4.Details
Week 1 - Foundations of Convolutional Neural Networks
- Programming Assignment: Convolutional Model: step by step
- Programming Assignment: Convolutional model: application
Week 2 - Deep Convolutional Models: Case Studies
Week 3 - Object Detection
Week 4 - Special Applications: Face Recognition & Neural Style Transfer
Sequence Models
5.Details
Week 1 - Recurrent Neural Networks
- Programming Assignment: Building a recurrent neural network - step by step
- Programming Assignment: Dinosaur Island - Character-Level Language Modeling
- Programming Assignment: Jazz improvisation with LSTM
Week 2 - Natural Language Processing & Word Embeddings
Week 3 - Sequence Models & Attention Mechanism
Contributing
- Please refer to CONTRIBUTE.md for details. 😍
License
Coursera is licensed under the MIT license.