KEMBAR78
AI-ML-DS (Level-2) Lab Lesson Plan | PDF | Artificial Intelligence | Intelligence (AI) & Semantics
Scribd
Upload
37 views2 pages

AI-ML-DS (Level-2) Lab Lesson Plan

The document outlines a lesson plan for the AI-ML-DS course at the University of Global Village, detailing 18 lessons covering topics such as Recurrent Neural Networks, Generative Adversarial Networks, Natural Language Processing, and model deployment. Each lesson includes specific learning objectives and practical applications, culminating in a final project that involves real-world problem-solving and model training. The course aims to equip students with essential skills in AI and machine learning, preparing them for careers in the field.

Uploaded by

MD. MINHAJ UL ISLAM
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
37 views2 pages

AI-ML-DS (Level-2) Lab Lesson Plan

The document outlines a lesson plan for the AI-ML-DS course at the University of Global Village, detailing 18 lessons covering topics such as Recurrent Neural Networks, Generative Adversarial Networks, Natural Language Processing, and model deployment. Each lesson includes specific learning objectives and practical applications, culminating in a final project that involves real-world problem-solving and model training. The course aims to equip students with essential skills in AI and machine learning, preparing them for careers in the field.

Uploaded by

MD. MINHAJ UL ISLAM
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

University of Global Village (UGV), Barishal.

Lesson Plan: CSE Lab Courses


Course Name AI-ML-DS

Course Code CSE

Semester 6th

Course Level 02

Supervisor Md. Minhaj Ul Islam

Instructor/Assistant Ahad Khan

Lesson Lesson Title Lesson Details Remarks


No

1. Recurrent Neural Learn about sequence modeling and text


Networks (RNNs) & generation. Train an RNN or LSTM for
LSTMs text-based tasks.

2. Generative Adversarial Understand the concept of GANs and how


Networks (GANs) Basics they generate new images.

3. ML/DL Mini Project Choose a dataset and apply ML/DL


concepts to build an end-to-end model.

4. Introduction to Generative Explore Large Language Models (LLMs)


AI like ChatGPT and Midjourney. Understand
how generative AI differs from traditional
ML/DL.

5. Natural Language Learn text preprocessing techniques,


Processing (NLP) Basics - tokenization, and lemmatization for NLP
Part 1 tasks.

6. Natural Language Understand TF-IDF and word embeddings.


Processing (NLP) Basics - Perform sentiment analysis on tweet data.
Part 2
University of Global Village (UGV), Barishal.
7. Transformers & Attention Learn how self-attention works and explore
Mechanism BERT architecture.

8. Fine-Tuning NLP Tasks Fine-tune models for text classification and


Named Entity Recognition (NER).

9. Text Generation with GPT Understand GPT tokenization and attention


Models mechanisms. Generate text using Hugging
Face’s GPT-2.

10. Image Generation with Learn about diffusion models like DALL·E
Stable Diffusion and Stable Diffusion. Generate AI-powered
images.

11. Building AI Chatbots with Use LLMs to create chatbots using


LangChain LangChain.

12. Agentic AI Explore autonomous AI agents and their


applications. Build an AI agent for a
specific task.

13. Retrieval-Augmented Learn how RAG combines retrieval-based


Generation (RAG) and generative models. Build a document-
based Q&A chatbot.

14. Model Deployment & API Convert models into APIs using FastAPI
Building and deploy them with Streamlit.

15. AI in Industry & Career Explore AI applications across industries.


Guidance Get resume and interview tips for AI roles.

16. Final Project - Part 1 Choose a real-world problem, collect


(Problem Selection & relevant data, and preprocess it for model
Data Preparation) training.

17. Final Project - Part 2 Train a machine learning or deep learning


(Model Training & model and evaluate its performance.
Evaluation)

18. Final Project Presentation Present insights, results, and key learnings
& Wrap-Up from the final project. Discuss future
learning paths in AI/ML.

You might also like