Hi there! 👋 I'm a passionate Python Developer with a knack for creating meaningful and impactful projects. My primary focus revolves around data analysis, financial simulations, and building intuitive tools and applications. Let's dive into what makes this space awesome!
- Spiking Neural Networks (SNN):
- Implementation with SNNTorch
- Hybrid MLP-SNN architectures
- Leaky Integrate-and-Fire neurons
- Evolutionary Algorithms:
- Performance-based selection
- Adaptive mutation
- Population-based training
- Reinforcement Learning:
- Multi-agent environments
- Hierarchical reward systems
- Intrinsic curiosity mechanisms
- Hybrid Architecture:
- PyTorch + SNNTorch integration
- MVC pattern for complex systems
- Residual blocks & multi-head attention
- Optimization:
- NumPy vectorization
- PyTorch parallelism
- RL resource management
- Testing & Validation:
- Unit tests for NN components
- Evolutionary policy validation
- Training metrics monitoring
| Domain | Key Libraries |
|---|---|
| Deep Learning | PyTorch, SNNTorch, TorchVision |
| Neuroscience | BindsNET, Nengo |
| Simulation | PyGame, Matplotlib |
| CI/CD | GitHub Actions, pytest |
| Analysis | Pandas, Seaborn, Plotly |
- Autonomous Systems:
- Spatial memory navigation
- Hierarchical decision-making
- Limited resource management
- Experimental Research:
- Transfer learning between agents
- Predator-prey dynamics
- Scalable dynamic environments
- Core Concepts: Variables, operators, conditional structures, loops
- Data Structures: Lists, dictionaries, tuples for versatile data storage
- Functions: Building reusable tools with parameters and return values
- Error Handling: Robust validations using
try/except - String Manipulation: Formatting data for user-friendly outputs
- Object-Oriented Programming (OOP):
- Modular architecture with MVC patterns
- Specialized classes with inheritance
- Use of
@propertydecorators for advanced validations
- Scientific Libraries:
- NumPy: Handling financial calculations like future value
- Pandas: Tracking and analyzing simulation histories
- SciPy: Optimizing complex calculations
- Testing Frameworks:
- pytest: Automating unit and functional tests
- unittest: Ensuring UI functionality
- Design Patterns: Implementing Factory Method, Observer, and Strategy for scalable solutions
- Concurrency & Parallelism:
- Threading for heavy computations
- Asyncio for efficient I/O
- Financial Integrations:
- Pulling real-time market data from APIs like Yahoo Finance
- Interactive Visualizations:
- Plotly: Stunning, interactive charts
- Dash/Streamlit: Web-friendly dashboards
- Type Hints & Documentation:
- Clear and maintainable codebases with type annotations and docstrings
📂 Highlighted Project: 🧠 SNN Evolutionary AI Testbed
🧠⚡ SNN Evolutionary AI Testbed
An experimental AI project testing Spiking Neural Networks (SNN) in complex multi-agent environments using evolutionary algorithms.
📌 Overview
This project simulates autonomous agents with hybrid neural architectures (MLP + SNN) that learn to collect trash efficiently while managing limited battery resources. It serves as a testbed for:
- Evolutionary training methods
- Spiking Neural Networks in complex environments
- Multi-agent reinforcement learning dynamics
- Memory-augmented navigation strategies
📂 Highlighted Project: 📈 Compound Interest Calculator
A powerful Compound Interest Calculator built with Python, designed for both educational and practical use cases.
It features:
- Customizable simulations
- Historical data tracking
- Exportable reports in PDF format
- Add persistence with SQLite
- Implement exportable reports in PDF
- Introduce internationalization (i18n) for global usability
- Build a loan simulator
- Create an investment comparison tool
- Develop a portfolio tracking bot
- Deploy web-based versions using FastAPI or Streamlit
- Build mobile apps using Kivy or BeeWare
- Establish CI/CD pipelines with GitHub Actions
- 📧 Email: ff3451054@gmail.com
- 💼 LinkedIn: David Rodrigues Resende
Thank you for visiting! 😊 Let's collaborate and build something exceptional together. 🚀✨