Instructed by
Laurence Moroney
Welcome! This repository is a collection of the work I completed while earning the TensorFlow Developer Professional Certificate from DeepLearning.AI.
Throughout the course, I gained hands-on experience in building and training deep learning models using TensorFlow 2.x and Keras. The program covered key areas such as computer vision, natural language processing, and time series forecasting. I explored different types of neural networks, including CNNs, GRUs, and LSTMs, and learned how to apply them to real-world problems.
Along the way, I also developed a solid understanding of:
- Optimization techniques like Adam, SGD, and RMSprop
- Regularization strategies such as L1/L2 and Dropout
- Data preprocessing and augmentation
- Batch normalization and callbacks
- Loss functions, evaluation metrics, and sequential model design
This course was a deep dive into the world of deep learning, offering both theoretical knowledge and practical experience. It helped me build a strong foundation in TensorFlow and gave me the tools to train effective models for a variety of AI tasks.
Feel free to browse through the projects and practice exercises I've shared here. Hope you find them useful!
Please, check Coursera Honor Code before you take a look at the assignments.
For more you can check course info.
-
Course 1 - Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
-
Week 1 - A New Programming Paradigm
-
Assigment:
- Housing Prices: C1W1_Assignment.ipynb
-
Ungraded Labs:
- Hello World Neural Network: C1_W1_Lab_1_hello_world_nn.ipynb
-
Quiz:
-
-
Week 2 - Introduction to Computer Vision
-
Assigment:
- Handwriting Recognition: C1W2_Assignment.ipynb
-
Ungraded Labs:
- Beyond Hello World, A Computer Vision Example: C1_W2_Lab_1_beyond_hello_world.ipynb
- Callbacks: C1_W2_Lab_2_callbacks.ipynb
-
Quiz:
-
-
Week 3 - Enhancing Vision with Convolutional Neural Networks
-
Assigment:
- Improve MNIST with Convolutions: C1W3_Assignment.ipynb
-
Ungraded Labs:
- Improving Accuracy with Convolutions: C1_W3_Lab_1_improving_accuracy_using_convolutions.ipynb
- Exploring Convolutions: C1_W3_Lab_2_exploring_convolutions.ipynb
-
Quiz:
-
-
Week 4 - Using Real-world Images
-
Assigment:
- Handling Complex Images: C1W4_Assignment.ipynb
-
Ungraded Labs:
- Preprocessing Images to Train a Neural Network: C1_W4_Lab_1_image_data_preprocessing_no_validation.ipynb
- Image Data Preprocessing with a Validation Set: C1_W4_Lab_2_image_data_preprocessing_with_validation.ipynb
- Compacted Images: C1_W4_Lab_3_compacted_images.ipynb
-
Quiz:
-
-
-
-
Week 1 - Exploring a Large Dataset
-
Assigment:
- Cats vs. Dogs: C2W1_Assignment.ipynb
-
Ungraded Labs:
- Using more sophisticated images with Convolutional Neural Networks: C2_W1_Lab_1_cats_vs_dogs.ipynb
-
Quiz:
-
-
Week 2 - Augmentation: A technique to avoid overfitting
-
Assigment:
- Cats vs. Dogs using Augmentation: C2W2_Assignment.ipynb
-
Ungraded Labs:
- Cats vs. Dogs with Augmentation: C2_W2_Lab_1_cats_v_dogs_augmentation.ipynb
- Horses vs. Humans with Augmentation: C2_W2_Lab_2_horses_v_humans_augmentation.ipynb
-
Quiz:
-
-
-
Assigment:
- Horses vs. Humans using Transfer Learning: C2W3_Assignment.ipynb
-
Ungraded Labs:
- Exploring Transfer Learning: C2_W3_Lab_1_transfer_learning.ipynb
-
Quiz:
-
-
Week 4 - Multiclass Classifications
-
Assigment:
- Multi-class Classifier: C2W4_Assignment.ipynb
-
Ungraded Labs:
- Classifying Rock, Paper, and Scissors: C2_W4_Lab_1_multi_class_classifier.ipynb
-
Quiz:
-
-
-
-
-
Assigment:
- Explore the BBC News Archive: C3W1_Assignment.ipynb
-
Ungraded Labs:
- Building a Vocabulary: C3_W1_Lab_1_building_a_vocabulary.ipynb
- Simple Sequences: C3_W1_Lab_2_sequences_basic.ipynb
- Sarcasm: C3_W1_Lab_3_sarcasm.ipynb
-
Quiz:
-
-
-
Assigment:
- Categorizing the BBC News Archive: C3W2_Assignment.ipynb
-
Ungraded Labs:
- Positive or Negative IMDB Reviews: C3_W2_Lab_1_imdb.ipynb
- Sarcasm Classifier: C3_W2_Lab_2_sarcasm_classifier.ipynb
- IMDB Review Subwords: C3_W2_Lab_3_imdb_subwords.ipynb
-
Quiz:
-
-
-
Assigment:
- Exploring Overfitting in NLP: C3W3_Assignment.ipynb
-
Ungraded Labs:
- IMDB Subwords with Single Layer LSTM: C3_W3_Lab_1_single_layer_LSTM.ipynb
- IMDB Subwords with Multi Layer LSTM: C3_W3_Lab_2_multiple_layer_LSTM.ipynb
- IMDB Subwords with 1D Convolutional Layer: C3_W3_Lab_3_Conv1D.ipynb
- IMDB Reviews with GRU (and optional LSTM and Conv1D): C3_W3_Lab_4_imdb_reviews_with_GRU_LSTM_Conv1D.ipynb
- Sarcasm with Bidirectional LSTM: C3_W3_Lab_5_sarcasm_with_bi_LSTM.ipynb
- Sarcasm with 1D Convolutional Layer: C3_W3_Lab_6_sarcasm_with_1D_convolutional.ipynb
-
Quiz:
-
-
Week 4 - Sequences Models and Literature
-
Assigment:
- Writing Shakespeare with LSTMs: C3W4_Assignment.ipynb
-
Ungraded Labs:
- NLP with Irish Music: C3_W4_Lab_1.ipynb
- Generating Poetry from Irish Lyrics: C3_W4_Lab_2_irish_lyrics.ipynb
- (Optional) Generating text using a character-based RNN: C3_W4_Lab_3_text_generation.ipynb
-
Quiz:
-
-
-
-
Week 1 - Sequences and Prediction
-
Assigment:
- Create and Predict Synthetic Data: C4W1_Assignment.ipynb
-
Ungraded Labs:
- Time Series: C4_W1_Lab_1_time_series.ipynb
- Forecasting: C4_W1_Lab_2_forecasting.ipynb
-
Quiz:
-
-
Week 2 - Deep Neural Networks for Time Series
-
Assigment:
- Predict with a DNN: C4W2_Assignment.ipynb
-
Ungraded Labs:
- Preparing Features and Labels: C4_W2_Lab_1_features_and_labels.ipynb
- Single Layer Neural Network: C4_W2_Lab_2_single_layer_NN.ipynb
- Deep Neural Network: C4_W2_Lab_3_deep_NN.ipynb
-
Quiz:
-
-
Week 3 - Recurrent Neural Networks for Time Series
-
Assigment:
- Using RNN's and LSTM's for time series: C4W3_Assignment.ipynb
-
Ungraded Labs:
- Recurrent Neural Network (RNN): C4_W3_Lab_1_RNN.ipynb
- Long Short-Term Memory (LSTM): C4_W3_Lab_2_LSTM.ipynb
-
Quiz:
-
-
Week 4 - Real-World Time Serie Data
-
Assigment:
- Daily Minimum Temperatures in Melbourne - Real Life Data: C4W4_Assignment.ipynb
-
Ungraded Labs:
- Long Short-Term Memory (LSTM): C4_W4_Lab_1_LSTM.ipynb
- Sunspots: C4_W4_Lab_2_Sunspots.ipynb
- Sunspots - DNN Only: C4_W4_Lab_3_DNN_only.ipynb
-
Quiz:
-
-
DeepLearning.AI TensorFlow Developer Professional Certificate