| Data Science Lifecycle |
Lecture |
120 min |
Introduction to the overall data science process. |
| Framing a Data Science Problem |
Lecture |
120 min |
Identifying, scoping, and translating problems into data science workflows. |
| Deep Learning Computer Vision |
Lecture/Lab |
120 min |
Overview of machine learning libraries and toolchains such as scikit-learn, pandas, and PyTorch. |
| Building and Optimizing Neural Networks with Pytorch |
Lecture/Lab |
120 min |
Build and optimize neural networks using PyTorch. |
| Neural Network Architectures |
Lecture |
120 min |
Explore key neural network architectures such as feedforward networks, CNNs, and RNNs. |
| Lab: Feedforward Neural Network |
Lab |
120 min |
Hands-on implementation of a feedforward neural network. |
| Foundations of Modern NLP |
Lecture |
120 min |
Introduction to natural language processing and modern NLP approaches. |
| Pipelines |
Lecture/Lab |
60 min |
Build end-to-end NLP pipelines. |
| Transformers |
Lecture/Lab |
120 min |
Understand transformer architectures and how they are used in modern AI systems. |
| Evaluating NLP Models |
Lecture/Lab |
90 min |
Techniques for evaluating and fine-tuning NLP and LLM models. |
| NLP Lab |
Lab |
120 min |
Practical NLP exercises applying the concepts learned in earlier modules. |
| AI Engineering: Prompt Engineering |
Lecture/Lab |
120 min |
Learn how to craft effective prompts for generative AI systems. |
| AI Engineering: Fundamentals of Chaining |
Lecture/Lab |
120 min |
Build multi-step AI workflows by chaining prompts and tools. |
| AI Engineering: Vector Databases and QA |
Lecture/Lab |
120 min |
Use vector databases for retrieval-augmented question answering systems. |
| Total content |
Total |
~26 hours |
|