In recent years, chatbots powered by GPT (Generative Pre-trained Transformer) models have revolutionized the way businesses and individuals automate tasks such as customer support and content generation. With GPT-3 in 2020, these chatbots have become even more sophisticated, able to generate human-like responses and carry out complex tasks. However, using…

Whenever we think of android app development android studio is the first tool that pops up in our minds. It is an environment that includes various tools for developing android applications. Java or Kotlin is the default language that android studio supports for development. However, most of the machine learning/deep…

Whenever we think of neural networks, GPUs automatically pop into our minds because they are very compute-heavy and often require powerful GPUs to train them. Most of the state-of-the-art models require GPUs even for fast inference which makes them not so cost-friendly for the end users. Often while deploying neural…

As machine learning practitioners, we often come across situations where we want to train a model which is relatively larger and our poor GPU is unable to train it because it doesn’t have enough memory. This problem often arrives while we are working in an environment where cloud computing is…

Pruning and quantization are way-to-go techniques for optimizing any deep learning model as used very commonly in model ops. However, in most cases, pruning is usually used as a model compression technique rather than for improving performance. Most of the libraries like PyTorch perform unstructured pruning and hence the performance…

Neural architecture search is a technique that automates the designing of neural networks for solving a particular problem. It was initially developed by researchers for people who are domain experts in a particular field but have very little or no machine-learning knowledge and want to develop machine-learning systems to solve…

Deployment is the most crucial step in any machine learning development cycle as it decides how much value a model will earn in an organization. YOLO is one of the most popular object detection available. Recently released YOLO v7 is the state-of-the-art object detection as of now and it's increasingly…

Deployment is the most crucial aspect of a machine learning project as most models end up being discarded either because they aren’t fast enough or are too expensive to deploy on the server. Every organization wants to build a model which is accurate and cheap for deployment. They also want…

It was my third year of BTech when I came across Tesla autonomy day on youtube where Andrej Karpathy was giving a presentation on the neural networks they developed for their self-driving system. I was totally mesmerized. This motivated me to create a self-driving toy car. I discussed the same…