Free Deep Learning Path

Comprehensive deep learning specialization by Andrew Ng. Master neural networks, CNNs, RNNs, and modern deep learning architectures.

Master convolutional neural networks and modern computer vision architectures for image classification and object detection.

This certification provides a comprehensive understanding of machine learning, deep learning, and AI ethics. It is designed for professionals interested in the intersection of AI and blockchain, covering AI integration in business processes, data analytics, and automation with hands-on labs.

An interactive deep learning book with code, math, and discussions. It includes a chapter on training on multiple GP Us, covering both from-scratch implementations and concise implementations using deep learning frameworks.

For those with an intermediate to advanced understanding of computer vision, this course covers advanced topics like deep learning, convolutional neural networks (CNNs), object detection, image segmentation, and generative models. It is taught by a renowned expert in the field and is designed for students with a strong programming background.

A deep learning course that offers a comprehensive introduction to Autoencoders, Variational Autoencoders (VAEs), and Generative Adversarial Networks (GANs).

This course provides a comprehensive overview of how machine learning functions in embedded systems. It teaches students how to train neural networks and deploy them to microcontrollers, a field also known as TinyML. The course is designed for beginners with no prior machine learning experience, but some familiarity with Arduino and microcontrollers is recommended.

An in-depth exploration of machine learning applications in cybersecurity, focusing on techniques for threat detection and prevention. Participants will gain a solid grounding in machine learning fundamentals, including neural networks, clustering, and support vector machines, tailored specifically for cybersecurity contexts.

This course covers the basic principles of machine translation, focusing on statistical and neural machine translation, including the current state-of-the-art neural machine translation technology which uses deep learning methods.

This beginner-level course introduces the concepts of linear algebra that are relevant to AI, machine learning, and deep learning.

This is the first course in the Machine Learning Specialization. It provides a broad introduction to modern machine learning, including supervised learning (linear regression, logistic regression, neural networks, and decision trees). You will build machine learning models in Python using popular machine learning libraries Num Py and Scikit-Learn.

A 2-hour project-based course where you will learn to understand and write a custom dataset class for an Image-mask dataset. You will also apply segmentation augmentation and load a pretrained state-of-the-art convolutional neural network for segmentation.

A guided project that teaches the fundamentals of using TensorFlow for image classification. You will build, train, and evaluate a neural network to classify images from the CIFAR-10 dataset.

A comprehensive book that starts with beginner topics like graph theory and traditional graph approaches and moves to more advanced topics such as novel GNN models and state-of-the-art research. It is a self-contained resource with most of the required theory for graph neural networks.

A comprehensive chapter on optimization algorithms for deep learning from the highly-regarded Deep Learning book.

Deep Learning Nanodegree Program

Computer Vision with Deep Learning