The course covers deep learning fundamentals and TensorFlow workflows:

1. Neural Network Basics: Perceptrons, activation functions, and backpropagation.
2. TensorFlow Framework: Tensors, layers, models, and training loops.
3. Model Architectures: CNNs, RNNs, and feedforward networks.
4. Optimization & Regularization: Loss functions, optimizers, dropout, and batch normalization.
5. Project Work: Build and train deep learning models for image or text data.

Modules are designed to build deep learning and TensorFlow skills:

• Weekly coding labs and architecture walkthroughs.
• Mini-projects focused on image classification and sequence modeling.
• Peer reviews and model tuning sessions.
• Capstone project: Build and present a deep learning model for a real-world dataset.

Classes are held twice weekly:

• One lecture session covering deep learning theory and TensorFlow demos.
• One lab session for hands-on model building and training.
• Optional office hours for mentoring and debugging support.

This course teaches how to build and train deep learning models using TensorFlow. It emphasizes architecture design, optimization, and real-world applications.

By the end, students will be able to implement neural networks for image, text, and structured data.

• Master deep learning concepts and TensorFlow workflows.
• Build and train neural networks for various data types.
• Prepare for roles in AI development and research.
• Build a portfolio of deep learning projects.