Deep Learning for Computer Vision
About Deep Learning for Computer Vision:
Deep learning added a boost to the already rapidly developing field of computer vision. With deep learning ,a lot of new applications of computer vision techniques have been introduced and are now becoming parts of our everyday lives. These include image and video processing such as face recognition and indexing, machine vision in self-driving cars. The goal of this course is to cover important aspects of computer vision, starting from basics and then tuning the more modern deep learning models. We will provide both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and editing and new image generation.
What you'll learn ?
By the end of this deep learning course with TensorFlow, you will be able to accomplish the following:
- Implement deep learning algorithms, understand neural networks and traverse the layers of data abstraction
- Master advanced topics such as convolutional neural networks, and adversarial Neural Networks mainly for Computer Vision.
- Learn how to build face recognition and manipulation system to understand the internal mechanics of this technology, probably the most renown and mostly demonstrated in movies and TV-shows example of computer vision and AI.
- Build your own deep learning project
- Know how to build a neural network in Theano and/or Tensorflow
- Multivariate Calculus
- Numpy, etc.
- A basic knowledge of Data Science and Machine Learning.
- Identify the deep learning algorithms which are more appropriate for Computer Vision.
- Able to work on Images and Videos and perfrom various tasks like object detection, frame prediction and etc.