Posts

Showing posts from May, 2022

My 2nd internship with oasis infobyte.

  Hi, I'm Prateek kumar Singh . In this blog I am going to share my internship experience which I got at # Oasis InfoByte . This was my first ever internship at # oasis infobyte and I'm happy that I got this opportunity . This was about Web Development and designing and in this internship we have to perform four tasks. These tasks are very beginner friendly but after completing this task you feel satisfaction that you can create website like we use to see everyday on our computer. But the thing that pains me is that despite such a wonderful opportunity to gain more and more skills and grow my self . I couldn't perform no more than 1 task that was portfolio website.  I couldn't avoid the problems that came this month.  This internship was about 1 month long. They gave us 4 tasks to complete within 1 month i.e., 1 task for a week. Generally everyone acquire skill and thought that he/she will get job but before applying job it is very important to know how to use that ski

Convolutional Neural Networks

  Convolutional Neural Networks What are convolutional neural networks? A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other. How do convolutional neural networks work? A CNN takes in a large amount of image data and utilizes multi channeled images. Due to digital color images having red-blue green (RGB) encoding, a convolutional network ingests such images as three separate strata of color stacked one on top of the other. The depth layers in the three layers of colors(RGB) interpreted by CNNs are referred to as channels. Layers in CNN • Convolutional Layer: It is the main building block of CNN. It contains all the filters, parameters of which are to be learned throughout the training. • Pooling Layer: It is used to reduce the number of parameters to learn and the computation performed in the ne