Skip to content
View Kikumu's full-sized avatar
:octocat:
:octocat:

Block or report Kikumu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Kikumu/README.md

💫 About Me:

I’m currently working on: Developing a Retrieval Augmented Generation (RAG) model using Langchain and Ollama with advanced techniques to improve contextual relevance and interaction.

I’m looking to collaborate on: AI projects that focus on reinforcement learning, neural networks, and data-driven solutions, especially in real-world applications where model deployment and scalability are crucial.

I’m currently learning: Advanced actor-critic algorithms in reinforcement learning and preparing for the AWS Certified Machine Learning Specialty exam.

Ask me about: Machine learning model deployment, reinforcement learning techniques, or how AI can improve flood prediction and music recommendation systems.

Fun fact: I once combined heat camera data with AI-enhanced processing to improve vision in dense smoke environments—adapting to environmental changes better than traditional models!

🌐 Socials:

LinkedIn

💻 Tech Stack:

C# AWS Lua Python Windows Terminal Anaconda nVIDIA Django FastAPI Flask OpenCV MusicBrainz MicrosoftSQLServer MySQL SQLite Keras Matplotlib NumPy Pandas PyTorch scikit-learn Scipy TensorFlow GitHub Git GitHub Actions Confluence Jira Notion Raspberry Pi Postman Plex nVIDIA

📊 GitHub Stats:




Pinned Loading

  1. DCGAN-with-facedata DCGAN-with-facedata Public

    This repository Investigates DCGAN using facedata. Serves as a personal cautionary tale when working with GANS.

    Jupyter Notebook

  2. Reinforcement-Learning-repo Reinforcement-Learning-repo Public

    A repo where I look into the details and practice on how to properly utilize reinforcement learning

    Jupyter Notebook

  3. Contra-Lua Contra-Lua Public

    Genetic algorithm implemented using lua and bizhawk to play classic contra retro game

    Lua

  4. Flood-algo-draft Flood-algo-draft Public

    flood algo test suite(Prototyping using CNN-RNN)

    Jupyter Notebook

  5. LBCGAN LBCGAN Public

    Location based conditional gan - this is only for prototype purposes

    Jupyter Notebook