kunal saluja - ClearSignal

kunal saluja

PolyLoss : A new framework for loss functions

PolyLoss : A new framework for loss functions

Original Paper: [https://arxiv.org/pdf/2204.12511.pdf] Authors: Zhaoqi Leng, Mingxing Tan , Chenxi Liu , Ekin Dogus Cubuk , Xiaojie Shi, Shuyang Cheng ,Dragomir Anguelov [Waymo And Google] Summary Authors propose a new framework of loss functions, motivated by the Taylor series expansion of commonly used functions like cross entropy

The future is remote!

Import 2022-11-27 02:49

The future is remote!

💡SAAS (Software as a service) is going remote. Here are 4 reasons why remote jobs are here to stay: 1. Hiring globally means a massive increase on the supply-side (number of applicants). With the US unemployment levels at their lowest in history, it seems logical for many companies to hire

Short NLP Overview!

Import 2022-11-27 02:49

Short NLP Overview!

Outline * Introduction * Neural Network Modeling * Available resources * References Introduction Natural language processing (NLP) is a branch of science sitting at the intersection of computer science, artificial intelligence, and computational linguistics. To put it simply, it gives computers the ability to read, understand and generate text and speech just like we

tweets Featured

Stock buybacks

Here's my tweet about stock buybacks Fed buys corporate bonds Rightwards arrow Companies buyback stock Rightwards arrowStocks are artificially inflated Rightwards arrow Companies pay back bonds on maturity(5-20 years later) just using the dividends on stocks they're already holding, if they grow at a modest rate. — Kunal Saluja (@_kunal_

1 Hour SAAS MBA

tweets Featured

1 Hour SAAS MBA

Every SAAS operator must read these articles by the one and only, David Sacks, the modern-day king of SAAS! Year In Review: my business blogs on SaaS fundamentals… 1) The SaaS Board Meetinghttps://t.co/q6g3UFrspb 2) The SaaS Org Charthttps://t.co/6ZIGO8Jlx1 3) The SaaS Metrics That Matterhttps:

My New Desktop!

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. But wait, should I get a laptop, a pre-built desktop, or just build my own ? It took me

EfficientNet (V1 & V2) - A smart heuristic

EfficientNet (V1 & V2) - A smart heuristic

Intuition EfficientNet tries to come up with a smart heuristic to scale a CNN, relating resolution, width, and depth of a CNN. In particular, it tries to answer two key questions: * What should be the best base network * How to scale the base network(a) in an efficient manner EfficientNet

Designing and shipping a ML Feature

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 on the model accuracy? These are some questions a typical machine learning team deals with on a daily basis. But it is important to not get

Semantic Segmentation - DeepLab V3+

Semantic Segmentation - DeepLab V3+

Semantic Segmentation Semantic segmentation involves partitioning/marking regions in the image belonging to different objects/classes. Deep learning methods have made a remarkable improvement in this field within the past few years. This short article summarises DeepLab V3+, an elegant extension of DeepLab v3 proposed by the same authors (Chen

CPU vs GPU vs TPU

CPU vs GPU vs TPU

Introduction While most of the deep learning engineers/enthusiasts tend to focus on algorithms, they often forget about the hardware they use for training/inference. If you were to ask them about why a GPU/TPU is faster than a cpu, you'll often hear responses like "GPUs are optimized for

Detection/Classification metrics

Detection/Classification metrics

Problem Statement 1. Once we've trained multiple detection/classification models, how to choose the best model ? 2. Once we've chosen the best model, how to choose the optimum operating point (the best threshold) ? Solution There are two metrics which can help us here. If you've come across terms like AP,