Aayushi Bahukhandi

In real-world use cases,  it's a standard practice to treat development , test , and production systems differently because they have differing security, data, and privacy controls. No code is deployed directly to be presented before the user, firstly it is tested in a testing environment and if it works fine, only then it is deployed in the production system.  About the project - In this project, I have made 2 environments- one for testing and other for the production system . The code is pushed by the Developer to GitHub. The code is pulled into our system by a job of Jenkins and then it is tested in a Docker environment for its efficiency and working. If any changes or updates are needed to be done in the code, we do it in the testing environment. After successful testing, the code is deployed for the user. Setup - 1) Jenkins 2) GitHub 3) Git Bash 4) REDHAT8 Linux - Docker Jenkins Jobs - Job 1 - The developer pushes the code to GitHub. This job pull

Transfer Learning in Deep Neural Networks - The easiest way to describe transfer learning is the  use of previously acquired knowledge and skills in new  learning  or problem-solving situations.  This is the same way in which we humans learn something . Humans have an inherent ability to transfer knowledge across tasks.   What we acquire as knowledge while learning about one task, we utilize in the same way to solve related tasks. The more related the tasks, the easier it is for us to transfer, or cross-utilize our knowledge.  Some simple examples would be - - Know how to ride a motorbike ⮫ Learn how to ride a car - Know how to play classic piano ⮫ Learn how to play jazz piano In transfer learning, we reuse t he weights of one or more layers from a pre-trained neural network model in our new model and either keeping the weights fixed, fine tuning them, or adapting the weights entirely when training the model. I've used the concept of transfer learning in deep ne