Welcome to the CSOC ML Week 2, dear ML enthusiasts! This week we move beyond image classification, and learn how convolutional networks can be applied to other core computer vision tasks. We will see fully convolutional networks equipped with downsampling and upsampling layers can be used for detection and segmentation tasks, and also learn about Sequence Models and Recurrent Neural Networks.
Before we get started it is important that you have completed these things:
Neural Networks and Deep Learning(resources provided in Week 0 and 1).
Convolutional Neural Networks course by Andrew NG(atleast till Week 3).
You must go thorugh the above(if not already done) to understand the basics of Convolutional Neural Networks and its appications.
This week, we will get started with Recurrent Neural Networks and their applications in Computer Vision tasks. So, lets go through the basics of RNNs first. The first week lectures in the course below will give you some key insights into the structure and working of RNNs.
To dive deeper into the working of Recurrent Nets you can go through the chapter given below:(optional)
This week we will learn about object detection and segmentation using computer vision.
YOLO: This is one of the most widely used one step object detection algorithms today. The article below will provide you an overview of the algorithm ans the intuition behind its working.