The field of AI is evolving at a very rapid pace but rarely does something happen that shifts the paradigm. The last two big things in the field of AI are Generative Adversarial Networks and attention mechanisms. Both of these techniques or methods have been used in countless research papers…

Everyone in the field of AI and ML knows about KNN but if you will dig deeper than you will know that KNN is not a good algorithm for the big datasets. Training time for KNN is O(1) whereas testing time is O(nd*m) (n=training samples, d=dimension of data, m=test samples)…

Have you ever wondered, why we need teachers to learn things? Why can’t we learn everything on our own once we have learnt how to read, write and comprehend? The problem lies in what to learn and how much to learn. A teacher has many years of experience and thus…

It's been a while since the inception of U-Net, the network was initially designed to do medical image segmentation but since then it’s been used for all sorts of segmentation tasks. In my limited experience, I’ve always found that segmentation works better than object detection (given that you have the…

Recently there was a huge shift in the field of computer vision and it was due to the application of transformers (an idea developed for NLP) to images and videos. Vision Transformers or ViT became hugely famous and it had beaten almost every other ConvNet based approach, followed by more…

In the last part of our R-programming series, we covered ANOVA, now it’s time to shift our focus to logistic and Poisson regression. Logistic regression is among one of the most famous algorithms in the entire classical machine learning. Logistic regression is still in use by companies like Google due…

ANOVA is a pretty famous tool to perform a lot of hypothesis testing, especially where the explanatory behavior (the one we want to predict) is categorical instead of numerical. In such cases, we can’t use regression models thus the need ANOVA or Analysis of Variance. …

In the last few blogs, we covered the basics of R programming through plots and visualization, then a little bit of theory about distributions and confidence intervals, followed by hypothesis testing and Linear regression. Often in the real world, the data we get is messy and we always need to…

Recently Meta-learning has gained a lot of popularity thus I decided to visit this amazing paper to explain why Meta-learning is gaining so much popularity. Before we go deep into this paper let’s throw some light on what’s meta-learning. Meta-learning refers to machine learning algorithms that learn from the output…