About Me: I’m Badreddin Balaj from Morocco, a Machine Learning Specialist with a strong focus on deep learning, generative models, NLP, and computer vision. I excel in interpreting and analyzing data using Python, R, and tools like TensorFlow, PyTorch, and scikit-learn.
Skills and Expertise: I have designed and implemented advanced deep learning models for various applications, including projects such as Falls Detection in Smart Home Environments, image classification, and object recognition using pre-trained models like VGG16 and XCEPTION. I’m well-versed in generative models for data and image generation, data augmentation, and creative content.
Educational Background: My educational journey includes mastering key mathematical concepts, providing a strong foundation for deep learning and data science. I’m committed to continuous learning and passionate about exploring the frontiers of deep learning, NLP, and computer vision. My skills encompass supervised and unsupervised learning, reinforcement learning, data cleaning, data exploration, and data visualization.
Summary: Implemented a Variational Autoencoder (VAE) for the Fashion MNIST dataset, showcasing the generation of new samples and exploring the latent space. The project covers data loading and preprocessing, VAE architecture definition, training, and sample generation.
Key Skills: Variational Autoencoder, Generative Models, Convolutional Neural Networks (CNN), TensorFlow, Deep Learning, Image Generation.
GitHub Repository: Variational Autoencoder for Fashion MNIST
Summary: Developed a comprehensive image classification system capable of classifying images of ten different animals using Convolutional Neural Networks (CNN). The project includes data organization, model building, training, feature extraction, fine-tuning, and model evaluation.
Key Skills: Image classification, TensorFlow, CNN, pre-trained models, deep learning, data organization, model training.
GitHub Repository: Ten Animals Classifier
For a more detailed explanation and code implementation, please refer to the Jupyter notebook and README in the GitHub repository.
For more projects, check the Projects section.
For more articles check the Articles section.