TensorFlow

ML model training

This project focuses on building a Lyric Classification Model using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Networks). The models' purpose is to identify which artist a given lyric belongs to. Users can input lyrics and the models will predict the associated artist, aligning with the course's focus on the practical implementation of Natural Language Processing (NLP) tasks.

A TensorFlow/Keras neural network for regression on noisy sine wave data, predicting continuous values with real-time visualization of predictions and loss using Matplotlib.

Trading Bot – Algorithmic Crypto Trading with AI Integration

This project is a powerful algorithmic trading bot for cryptocurrency markets. It combines traditional technical analysis with modern machine learning to generate accurate and intelligent trading decisions.

Key Features:

Candlestick Pattern Detection: Identifies classic reversal patterns such as Hammer, Doji, Engulfing, Shooting Star, and complex formations like triangle patterns.

Technical Indicators: Includes standard indicators (RSI, MACD, Moving Averages, Bollinger Bands) and advanced tools like Ichimoku Clouds, SuperTrend, Fibonacci Retracements, and more.

Machine Learning Integration: Uses LSTM-based models for time-series forecasting and momentum strategies, combined with indicator signals through weighted evaluation.

Dynamic Signal Weighting: Customizable signal weighting for patterns, indicators, and ML predictions with automatic adjustments to market volatility.

Trade Execution Engine: Supports long/short positions with stop-loss, take-profit, and trailing stop features. Automatically includes fees and tax deductions in profit calculations.

Backtesting & Debugging: Simulates strategies on historical data with detailed equity/value curve visualization and comprehensive debug logs.

Robust Error Handling: Detects and logs data inconsistencies, index errors, and processing issues to ensure stability.

Modular architecture with key components such as TraderBot, SignalHandler, PatternManager, IndicatorManager, MLModelHandler, SequenceManager, DataAPI, and CryptoCurrency. Additional support provided by PatternCalculator, IndicatorCalculator, and DataProcessing.

Version: V1.3.0.0 | GUI: V1.0.0 Author: Marian Seeger – info@seegersoftwaredevelopment.de

Android implementation of an offline computer vision algorithm for Malaria parasite detection and classification in thick blood smears (see research project).

A Computer Vision algorithm for Malaria parasite detection and classification in digital images of thick blood smears.

A project that utilizes machine learning to predict shrimp growth to optimize the amount of feed used.

This repository is a testament to my journey of learning Tensor Flow from scratch (basics to intermediate level) using Google’s official Tensor-Flow documentation.

Introduction to classification using machine learning and deep learning (PyTorch, TensorFlow, Keras)

Tutorials from tensorflow, for learning purposes

Repository of real applications of neural networks coded in Python with TensorFlow/Keras and PyTorch.

Cyber determetion toolskit

This project provides a deep learning approach to learn machining features from CAD models using a hierarchical graph convolutional neural network.

Linear regression refresher

This project aims to build a Celebrity Look-A-like Model using CNN (Convolutional Neural Networks) based on the VGG (Visual Geometry Group) 16 Model. Users can enjoy a lighthearted exploration of their celebrity doppelgängers. The project integrates image processing, CNN implementation, transfer learning and practical neural network applications, aligning with the course's focus on the practical implementation of Deep Neural Networks.

The project focuses on developing a predictive tool for chess using recurrent neural network (RNN) models implemented in TensorFlow. Data collection was carried out using web scraping techniques from the website https://www.chess-poster.com.

El proyecto se orienta hacia el desarrollo de una herramienta predictiva para el ajedrez, empleando modelos de red neuronal recurrente (RNN) implementados en TensorFlow. La recopilación de datos se realizó mediante técnicas de web scraping desde la página https://www.chess-poster.com.

This project builds a Lyric Generation Model using LSTM and CNN neural networks to create song lyrics across different genres. Focusing on NLP tasks, the model will be trained on a large corpus of song lyrics. To ensure portability and ease of deployment, the project will be Dockerized, allowing users to run the model seamlessly across different environments without setup issues. Docker will package all dependencies, providing a consistent workflow for development, testing, and production.