Blog

A collection of 17 posts tagged with "blog".

Notes - Grounded SAM
blog Featured

Notes - Grounded SAM

What is Grounded SAM? The Grounded SAM paper introduces a novel approach to open-set segmentation by combining two powerful pre-trained models...

2 min read
NOTES: Can LLMs truly reason?
papers Featured

NOTES: Can LLMs truly reason?

Can LLMs actually reason, or are they just “probabilistic pattern matchers”? This paper attempts to answer that question.

3 min read
Yolo-X Notes
papers Featured

Yolo-X Notes

The main motivation behind YOLOX was to update the YOLO series with the recent advancements at the time, particularly anchor-free detection.

2 min read
Multi-task Loss
blog

Multi-task Loss

This is a short review of the paper titled "Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics" by Kendall et al, 2018.

3 min read
SVD
blog Featured

SVD

SVD (Singular Value Decomposition) is one of my favorite topics in linear algebra. It's almost magical to factorize any matrix...

2 min read
Short NLP Overview!
blog

Short NLP Overview!

Natural language processing (NLP) is a branch of science sitting at the intersection of computer science, artificial intelligence, and computational linguistics.

6 min read
My New Desktop!
blog

My New Desktop!

If you're into gaming and deep learning, you need to own a GPU. For years I was working with an older GPU (GTX 960M), but I thought it was time to upgrade.

1 min read
Designing and shipping a ML Feature
blog Featured

Designing and shipping a ML Feature

What exactly are we trying to accomplish? Will the new model architecture really be a game-changer? How much impact will this new dataset have...?

2 min read
Semantic Segmentation - DeepLab V3+
papers

Semantic Segmentation - DeepLab V3+

Semantic segmentation involves partitioning/marking regions in the image belonging to different objects/classes. This short article summarises DeepLab V3+...

2 min read
Detection/Classification metrics
blog

Detection/Classification metrics

Once we've trained multiple detection/classification models, how to choose the best model? Once we've chosen the best model, how to choose the optimum operating point?

2 min read