Stanford Deep Learning Specialization

Built and trained deep neural networks, identified key architecture parameters, and implemented vectorized neural networks for real-world deep learning applications.

Created training, validation, and test pipelines, analyzed bias and variance in deep learning models, applied optimization techniques and best practices, and developed neural networks using TensorFlow.

Built and applied Convolutional Neural Networks (CNNs) for image classification, detection, and recognition tasks, implemented Neural Style Transfer, and developed deep learning solutions for image and video processing.

Built and trained Recurrent Neural Networks (RNNs), worked with Natural Language Processing (NLP) and Word Embeddings, and used Hugging Face tokenizers and Transformer models to perform Named Entity Recognition (NER) and Question Answering (QA).