The principles and most recent methods of deep learning and reinforcement learning are examined in this advanced course. Neural networks, TensorFlow, convolutional and recurrent neural networks, optimization, unsupervised learning, attention mechanisms, and deep reinforcement learning methods including intelligent agent design, function approximation, and policy learning are all covered. Leading researchers [...]

The foundational and advanced ideas of deep learning are introduced to students in this Udacity Deep Learning Nanodegree. Neural networks, backpropagation, convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs) are all covered in this course. Students develop useful abilities for resolving real-world AI issues [...]

Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola wrote an open-source book and a free interactive deep learning course. Through mathematical explanations, graphics, and executable Jupyter notebooks, it offers a practical method for studying deep learning. Linear algebra, neural networks, CNNs, RNNs, attention mechanisms, transformers, optimization, and [...]

Hugging Face offers a free, practical course that uses deep learning techniques to teach Natural Language Processing (NLP) and Large Language Models (LLMs). Learners work with datasets and tokenizers, investigate Transformer topologies, utilize the 🤗 Transformers library, refine pretrained models, and create useful NLP applications including text categorization, generation, translation, [...]

This Stanford course uses deep learning techniques to present fundamental ideas in Natural Language Processing (NLP). With a major emphasis on creating models that comprehend and produce human language, it includes word embeddings, recurrent neural networks, attention mechanisms, and transformer structures. The course blends theoretical underpinnings with real-world applications found [...]

To assist students in comprehending and creating deep learning models with the TensorFlow framework, IBM provides the “Deep Learning with TensorFlow” course. Important topics covered in the course include neural networks, deep learning architectures, training models, and using TensorFlow and Python to develop practical AI applications. It is appropriate for [...]

A set of free, practical learning tools called TensorFlow Developer Tutorials teaches developers how to use TensorFlow to create and train deep learning and machine learning models. Neural networks, computer vision, natural language processing (NLP), model training, deployment, and real-world AI applications with step-by-step examples are all covered in the [...]

Neural networks, training methods, computer vision, natural language processing (NLP), generative AI, and contemporary deep learning applications are all covered in this free introductory MIT course. The course integrates deep learning frameworks with real projects, practical coding exercises, and theoretical topics. [...]

Neural networks, deep learning principles, computer vision, natural language processing (NLP), generative AI, and real-world neural network implementation are all covered in this thorough introduction deep learning course. Lectures, coding laboratories, and practical AI applications are all part of the course. It is appropriate for students who have a basic [...]

An extensive overview of deep learning for computer vision is provided by this well-known Stanford University course. Convolutional Neural Networks (CNNs), object identification, image categorization, neural network training, optimization methods, and real-world application through assignments and projects are all covered. For students who wish to develop advanced abilities in computer [...]