This portfolio showcases a selection of diverse and innovative projects:
Categories: Natural Language Processing (NLP), Computer Vision, Fraud and Anomaly Detection, Prediction and Optimization, Recommendation and Personalization, Reinforcement Learning...
Discover a wide range of generative AI and machine learning projects, categorized by application domains. Click "Read More" to view project summaries and access GitHub links for source code and comprehensive documentation.
Neural style transfer
Highlights
- Developed an advanced TensorFlow pipeline for image stylization with custom enhancements and adjustable style intensity.
- Applied brightness, contrast, and saturation improvements to enhance visual quality of stylized outputs.
- Leveraged a pre-trained VGG19 model for accurate image classification and top-class prediction analysis.
Tags: image Stylization, Deep Learning, TensorFlow, Computer Vision, Image Classification
Try It
GitHub Repo
Read MoreTranslations [en,fr,es]
Highlights
- Built a CNN-LSTM encoder-decoder architecture to translate images into chemical formulas
- Developed a comprehensive PyTorch GPU/TPU image captioning pipeline
- Finished in the top 5% of the Kaggle competition leaderboard with a silver medal
- Achieved a 0.8925 F1 score on the test set
Tags: computer vision, natural language processing, deep learning
Try ItGitHub Repo Read MoreANN from scratch
Highlights
- Built a CNN-LSTM encoder-decoder architecture to translate images into chemical formulas
- Developed a comprehensive PyTorch GPU/TPU image captioning pipeline
- Finished in the top 5% of the Kaggle competition leaderboard with a silver medal
Tags: computer vision, natural language processing, deep learning
Try ItGitHub Repo Read MoreReasoning Model
Highlights
- Integrates Mistral 7B GGUF for advanced reasoning with an extended context (2048 tokens)
- Uses FAISS + SentenceTransformer to store and retrieve facts from a dynamic knowledge base.
- Implements strict logical reasoning with both standard and counterfactual analysis.
- Performs self-correction to ensure logical accuracy and consistency in responses.
Tags: NLP, logical reasoning, knowledge base, FAISS, deep learning
Try ItGitHub Repo Read MoreOther Projects
Curious to see more of my work? My journey in machine learning spans various domains, from generative AI to computer vision and data analysis.
Each project represents a unique challenge, where I apply cutting-edge techniques to solve real-world problems.
Below, you’ll find a selection of my projects categorized by application area. Feel free to check out my GitHub for more details and code implementations.
This is the content of item 1.
This is the card body. Your content is hidden initially. It is shown by clicking on the card header.
This is the content of item 3.
This is the content of item 3.
This is the content of item 3.
Demonstration Projects
These projects are designed to break down complex machine learning concepts into fundamental building blocks, providing a deeper understanding of how AI models function at their core.
ANN from Scratch
Artificial Brain
CNN from Scratch
Transformer Models
Machine Learning Fundamentals