Machine Learning

robot learning in library

Can you enhance reasoning abilities of LLMs with prompt engineering?

Today, I wanted to discuss an interesting topic that’s been on my mind – the reasoning abilities of Large Language Models (LLMs). You might already know that LLMs with 100B or more parameters can perform tasks like sentiment analysis and machine translation impressively well. However, they still struggle when it comes to certain multi-step reasoning […]

Can you enhance reasoning abilities of LLMs with prompt engineering? Read More »

Real-time writing with fingers on Web Camera-Screen

This can be used for quick explanation during office meetings or during online education classes. I have combined my two previous projects: 1. Hand tracking(21 landmark points) 2. Writing on-screen with the pre-identified object (Problem with this was: It was able to write with only previously identified color objects. And that too in a constrained environment.) so, combining

Real-time writing with fingers on Web Camera-Screen Read More »

Hand Tracking tool – Computer Vision (Machine learning)

I have made a hand gesture tracking tool. It can also track hand movements live through a webcam. To show its output, I have applied this tool on video. Output is as below: This project processes the input from the web camera. Then, It identifies 21 landmark points of hands. It runs smoothly on the

Hand Tracking tool – Computer Vision (Machine learning) Read More »

car price prediction

Case Study: Car price prediction. Multiple Linear regression solved with the statistical model

The problem is solved with the OLS regression model, REF, VIF, P values. (To clarify: OLS= Ordinary Least Square, RFE = Recursive Feature elimination, VIF= Variance Inflation Factor) Problem Statement and the Data Data consists of various car features such as car name, fuel type, engine type, engine size, car body, car width, car length, etc. The

Case Study: Car price prediction. Multiple Linear regression solved with the statistical model Read More »

Case Study: Breast Cancer Classification

Predicted if the cancer diagnosis is benign or malignant based on several observations/features. 30 features of tumor are used, examples: – radius (mean of distances from center to points on the perimeter)– texture (standard deviation of gray-scale values) – perimeter – area– smoothness (local variation in radius lengths) – compactness (perimeter^2 / area – 1.0)

Case Study: Breast Cancer Classification Read More »

Feature Scaling: Meaning and its importance in Machine Learning?

For Machine learning(ML), you deal with a large set of data with a lot of features. For instance, to predict housing prices, its features would be – an area of the land, number of rooms, size of rooms and kitchen, neighborhood, age of the building, land slope, proximity to the highway-railway-airport, etc. The algorithm sees

Feature Scaling: Meaning and its importance in Machine Learning? Read More »

Scroll to Top