Computer science student at University of Engineering and Management
Passionate ML Engineering student ThoughtWorks
Welcome to my repository, where I share website design projects and learning resources for beginners. This collection includes HTML, CSS, JS, and Python-based projects, aiming to provide a comprehensive learning experience for those new to web development.
I'm passionate about exploring the frontiers of artificial intelligence, with a deep focus on machine learning and Large Language Model (LLM) development. My work spans designing, training, and deploying AI agents capable of tackling complex real-world challenges and enhancing decision-making pipelines. I actively work with advanced natural language processing, predictive modeling, and neural network architecture design to push the boundaries of what's possible in AI and ML.
I have hands-on experience with Convolutional Neural Networks (CNNs), PyTorch, and large multimodal pipelines, particularly in the medical and geospatial domains. My projects include developing cancer image classification systems, satellite image segmentation, and rockfall detection models using OpenPilot and satellite imagery to support safety and monitoring in mining environments.
Currently, I’m expanding my expertise in Generative Adversarial Networks (GANs) and Transformer-based architectures deepening my understanding of modern LLMs and cutting-edge generative models. I'm continuously exploring innovative techniques to build scalable, robust, and high-impact AI systems.
I welcome contributions from anyone who wants to help improve my repo. Whether you're a seasoned developer or just starting out, your contributions are valued. This week I spent my time on
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
||
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
- 🌟 Passionate about combining creativity with tech.
- 🎯 2025 Goals: Build a personal ML project that makes an impact.
- ✨ Fun fact: Can spend hours debugging code but still feel victorious!
- 💡 Motto: "In programming, it's not about having no bugs, it's about learning how to squash them."
- 🤝 Open to collaborating on Python, ML, and creative tech projects.
- 🌍 Life Mission: To turn ideas into reality with the power of code!
Here is a clean, readable Mermaid flowchart in Markdown, showing: Machine Learning Algorithms Supervised Learning Unsupervised Learning Reinforcement Learning Each category includes the major algorithms under it.
%%{ init: { "flowchart": { "htmlLabels": false, "nodeSpacing": 40, "rankSpacing": 120 } } }%%
flowchart LR
A[Machine Learning Algorithms]
%% Main branches
A --> B[Supervised Learning]
A --> C[Unsupervised Learning]
A --> D[Reinforcement Learning]
%% Supervised Learning Algorithms
B --> B1[Linear Regression]
B --> B2[Logistic Regression]
B --> B3[Decision Trees]
B --> B4[Random Forest]
B --> B5[Support Vector Machines - SVM]
B --> B6[K-Nearest Neighbors - KNN]
B --> B7[Naive Bayes]
B --> B8[Gradient Boosting and XGBoost]
B --> B9[Neural Networks]
%% Unsupervised Learning Algorithms
C --> C1[K-Means Clustering]
C --> C2[Hierarchical Clustering]
C --> C3[DBSCAN]
C --> C4[Principal Component Analysis - PCA]
C --> C5[Autoencoders]
C --> C6[Gaussian Mixture Models - GMM]
C --> C7[Self Organizing Maps]
%% Reinforcement Learning Algorithms
D --> D1[Q-Learning]
D --> D2[Deep Q Networks - DQN]
D --> D3[SARSA]
D --> D4[Policy Gradient Methods]
D --> D5[Actor Critic Methods]
D --> D6[Proximal Policy Optimization - PPO]
horizontal Mermaid flowchart (LR) for Deep Learning with major categories and variants, similar to your ML chart. I’ll include FNN, RNN, CNN, GAN, Transformers, and other important variants like PointNet, LSTM, GRU, ResNet, Autoencoders etc.
%%{ init: { "flowchart": { "htmlLabels": false, "nodeSpacing": 40, "rankSpacing": 120 } } }%%
flowchart LR
A[Deep Learning Algorithms]
%% Main branches
A --> B[FNN - Feedforward Neural Networks]
A --> C[RNN - Recurrent Neural Networks]
A --> D[CNN - Convolutional Neural Networks]
A --> E[GAN - Generative Adversarial Networks]
A --> F[Transformer Networks]
A --> G[Autoencoders & Variants]
A --> H[Graph & Point Networks]
%% FNN Variants
B --> B1[Basic Feedforward Network]
B --> B2[Deep MLP - Multi Layer Perceptron]
%% RNN Variants
C --> C1[Simple RNN]
C --> C2[LSTM - Long Short-Term Memory]
C --> C3[GRU - Gated Recurrent Unit]
C --> C4[Bidirectional RNN]
C --> C5[Attention-based RNN]
%% CNN Variants
D --> D1[Basic CNN]
D --> D2[LeNet]
D --> D3[AlexNet]
D --> D4[VGGNet]
D --> D5[ResNet]
D --> D6[DenseNet]
D --> D7[Inception Network]
D --> D8[MobileNet]
%% GAN Variants
E --> E1[Vanilla GAN]
E --> E2[DCGAN - Deep Convolutional GAN]
E --> E3[WGAN - Wasserstein GAN]
E --> E4[CGAN - Conditional GAN]
E --> E5[StyleGAN]
%% Transformer Variants
F --> F1[Vanilla Transformer]
F --> F2[BERT - Bidirectional Encoder Representations]
F --> F3[GPT - Generative Pretrained Transformer]
F --> F4[Vision Transformer - ViT]
F --> F5[Encoder-Decoder Transformer]
%% Autoencoders Variants
G --> G1[Basic Autoencoder]
G --> G2[Variational Autoencoder - VAE]
G --> G3[Denoising Autoencoder]
G --> G4[Sparse Autoencoder]
%% Graph & Point Networks
H --> H1[Graph Neural Networks - GNN]
H --> H2[Graph Convolutional Networks - GCN]
H --> H3[Graph Attention Networks - GAT]
H --> H4[PointNet]
H --> H5[PointNet++]
