Foundations of Deep Learning & CNNs 

Unit 1. Data Collection & Web Scraping (Data Acquisition)

• Hands-on data collection using news, weather, and population web scraping notebooks

Unit 2. Data Preprocessing, Feature Engineering & AI Ethics (Preprocessing & Ethics)

• Imputation of missing values, data ethics, and feature engineering pipelines

Unit 3. Classical Machine Learning & Classification Algorithms (Classical Machine Learning)

• Regression vs. Decision Trees, Palmer Penguins classification, and Iris classification via Gradient Descent

Unit 4. Deep Learning Foundations & Artificial Neural Networks (Deep Learning Foundations)

• Linear regression with Keras, multi-layer perceptron on Fashion MNIST, and PyTorch fundamentals

Unit 5. Computer Vision, CNNs & Transfer Learning (Computer Vision & Transfer Learning)

• SSD face detection, MobileNetV2 classification, and face embedding verification using cosine similarity

Unit 6. Natural Language Processing & Machine Translation (NLP & Translation)

• NLTK tokenization and basics, TextBlob sentiment analysis, and MarianMT translation with BLEU score evaluation

Unit 7. Generative Models & Multimodal AI (Generative Models & Multimodal)