Advanced Machine Learning and Deep Learning Projects

Name: Advanced Machine Learning and Deep Learning Projects
Rating: 4.5 (271 reviews)

Text Embedding, Clustering, Classification | Image Clustering, Classification, Text to Image Search

Created byKGP Talkie | Laxmi Kant

Last updated 12/2025

English

English [Auto],

What you'll learn

Advanced NLP for Data Scientists
Advanced Image Processing
Text Data Processing
Text and Image Data Embeddings into the Same Vector Space
Implement Image Search like Google's Image Search
Cluster Text and Image Data

Course content

3 sections • 32 lectures • 5h 21m total length

Download Code Files0:04
Course Introduction!

SBERT Sentence Transformers Introduction5:18
SBERT Research Paper Review8:54
BERT Transformers Introduction9:34
Siamese Network in SBERT3:25
Explore how siamese networks with triplet loss power sentence transformers, generating BERT-based sentence embeddings to measure semantic similarity and enable semantic search and retrieval.
Project 1- Sentence Embeddings and Similarity Part 16:14
Learn to generate sentence embeddings and compare similarity with cosine similarity using sentence transformers and pre-trained models from Hugging Face, for sentences, paragraphs, or documents.
Project 1- Sentence Embeddings and Similarity Part 212:55
Learn to generate sentence embeddings with a pre-trained sentence transformer, compute cosine similarity across sentences, and use paraphrase mining to identify top matching documents.
Project 2- Semantic Search Introduction6:31
Project 2- Semantic Search Coding19:35
Project 3- K-Mean Clustering on Text Data13:06
Project 3- Agglomerative Clustering on Text Data13:20
Project 3- Fast Clustering on Quora Questions Set11:59
Apply fast text clustering on a large Quora questions set using sentence transformers and community detection to reveal meaningful clusters from 1000 samples.
Project 4- Build Quora Questions Auto-Complete Suggester - Part 18:01
Project 4- Build Quora Questions Auto-Complete Suggester - Part 211:55
Build a multilingual Quora questions auto-complete suggester by loading a sentence transformer model, encoding 37k questions into embeddings, and performing semantic search to return top-k related questions.
Project 5- Similar Research Paper Recommendation System Part 19:47
Explore a similar research paper recommendation system using sentence transformers to measure semantic similarity between a paper’s title and abstract, enabling symmetric search with the Specter algorithm.
Project 5- Similar Research Paper Recommendation System Part 28:11
Project 5- Similar Research Paper Recommendation System Part 39:30
Implement a deep search based recommendation system that embeds a paper title and abstract, then uses semantic similarity to surface the top three related research papers from the corpus.
Project 6- Question Answer Retrieval System using NLP Part 17:09
Project 6- Question Answer Retrieval System using NLP Part 210:13
Project 6- Question Answer Retrieval System using NLP Part 39:13
Build a question-answer retrieval system using NLP by encoding documents via corpus embedding and questions via question embeddings into a shared vector space, then apply semantic search for top matches.
Project 7- Extractive Text Summarization Part 17:04
Project 7- Extractive Text Summarization Part 212:07
Apply extractive text summarization with sentence transformers and LexRank to identify top central sentences by cosine similarity, demonstrated on a Hindustan Times article.

Project 1- Text to Image Search Introduction7:00
Project 1- Text to Image Search Coding Part 111:44
Set up a text-to-image search using sentence transformers and clip to embed text and images in a vector space, then code a live search with 2000 images in Google Colab.
Project 1- Text to Image Search Coding Part 214:47
Build a text-to-image and image-to-image search pipeline by projecting text and image data into a vector space and retrieving top results via semantic search with a clip model.
Project 2- Image Search from Hindi, Spanish, and French Text Data Part 112:15
Explore multilingual image search using sentence transformers and a multilingual clip model, enabling cross-language queries in Spanish, French, and more than 50 languages, via Google Colab.
Project 2- Image Search from Hindi, Spanish, and French Text Data Part 211:23
Embed images with img embed and text with a sentence transformer, then use semantic search and cosine similarity to retrieve top multilingual results across Hindi, Spanish, and French.
Project 3- Unsupervised Image Clustering Part 16:46
Project 3- Unsupervised Image Clustering Part 215:26
Continue unsupervised image clustering by building a cosine similarity-based community detector over image embeddings. Apply thresholds for minimum and maximum community sizes and similarity to form clusters.
Project 3- Unsupervised Image Clustering Part 311:33
Perform unsupervised image clustering, sort extracted communities by size, keep the largest cluster first, remove overlapping and duplicates, and present clusters with three images each, yielding 26 unique communities.
Project 4- Finding Duplicated Images and Near Duplicates11:53
Detect duplicate and near duplicate images by encoding with sentence transformers and clip, using cosine similarity and paraphrase mining to find top matches in the Unsplash dataset.
Project 5- Zero-Shot Image Classification14:37

Requirements

Basic programming of ML is desired
Experience in Python programming
Desire to learn

Description

This advanced machine learning and deep learning course will cover the following topics:

SBERT and BERT: These are pre-trained models that are used for natural language processing tasks such as sentence classification, named entity recognition, and question answering.
Sentence Embedding and Similarity Measures: Techniques for representing sentences as numerical vectors, and methods for comparing the similarity between sentences.
Clustering: Algorithms for grouping similar data points together, such as k-means and hierarchical clustering.
Text Summarization: Techniques for automatically generating a concise summary of a longer text.
Question Answering: Techniques for automatically answering questions based on a given text.
Image Clustering: Algorithms for grouping similar images together.
Image Search: Techniques for searching for images based on their content.

Throughout the course, students will work on hands-on projects that will help them apply the concepts they have learned to real-world problems. They will also get an opportunity to implement the latest state of the art techniques in the field to solve various NLP and CV problems.

By the end of this course, your confidence will boost in creating and analyzing the Image and Text Processing ML model in Python. You'll have a thorough understanding of how to use Text Data and Image Data modeling to create predictive models and solve real-world business problems.

How this course will help you?

This course will give you a very solid foundation in machine learning. You will be able to use the concepts of this course in other machine learning models. If you are a business manager or an executive or a student who wants to learn and excel in machine learning, this is the perfect course for you.

What makes us qualified to teach you?

I am a Ph.D. Scholar in Machine Learning and taught tens of thousands of students over the years through my classes at the KGP Talkie YouTube channel. A few of my courses are part of Udemy's top 5000 courses collection and curated for Udemy Business. I promise you will not regret it.

Who this course is for:

Who have basic knowledge of ML
Who want to skill up
Who want to boost their career

Advanced Machine Learning and Deep Learning Projects

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 1min

Natural Language Processing Projects21 lectures • 3hr 24min

Image Processing Projects10 lectures • 1hr 57min

Requirements

Description

Who this course is for: