Deep Learning For Visual Computing

Resumen

Deep learning revolutionizes how machines understand data by leveraging non-linear transformation architectures to solve hierarchical recognition tasks. Imagine a machine recognizing Mr.

X in a photo standing before Mt. E; features evolve from identifying shapes, colors, and edges to comprehending complex scenes and objects.

This course will guide you through the theory and practical coding aspects of applying deep learning algorithms, specifically in visual computing, using Python and PyTorch.

Participants will delve into tasks ranging from handwritten character recognition and object localization to advanced image captioning and synthetic image generation, all quintessential for technologies like self-driving cars. The course is designed for those with a background in digital image processing and machine learning, catering to students in electrical, electronics, and computer sciences.

Supported by industry giants including Intel, Microsoft, Google, and Nvidia, this course promises comprehensive insights beneficial for careers in deep learning and machine vision sectors.

Discover how to empower your skills in this cutting-edge domain through a program offered by the University of California, San Diego via Swayam.

• Intended Audience:

  Electrical, Electronics, Computer Sciences

• Prerequisites:

  Digital Image Processing, Machine Learning

• Supported by Industries:

  Intel, Microsoft, Google, Nvidia, Philips, GE, Siemens, Samsung, IBM, Apple, TCS, Infosys, Wipro, Robert Bosch, Baidu, Wymo, Tesla

• University:

  University of California, San Diego

• Provider:

  Swayam

• Categories:

  Artificial Intelligence, Python, Deep Learning, Neural Networks, Image Captioning, Autoencoders, Object Recognition

Materias