Sarvesh Kesharwani

I built and open-sourced **SafeNest**. A Windows app to lock private folders locally with AES-256-GCM encryption. No cloud. No login. No telemetry. Supports large video files over 2 GB. GitHub: github.com/Sarvesh-Keshar…

Just launched "ClipWise". A smarter way to learn from videos: watch in clips, track progress, revisit weak parts, and stay engaged instead of passively consuming content. If you learn from YouTube/tutorial videos, give it a try: clip-wise-alpha.vercel.app #startup #productivity

Just shipped my new Chrome extension: Amazon Product Filter 🛒 It helps you instantly filter products and sort listings by number of reviews so the most trusted products rise to the top.​ Try it here 👉 chromewebstore.google.com/detail/amazon-…

What's the difference between query and path In FastAPI? Path params are required and part of the URL (e.g. /user/1). Query params are optional and come after ? (e.g. /users?sort=asc). #FastAPI #Python

FREE Statistics Courses- mltut.com/best-free-onli… @KirkDBorne @antgrasso @ronald_vanloon #MachineLearning #DeepLearning #BigData #Datascience #ML #HealthTech #DataVisualization #ArtificialInteligence #SoftwareEngineering #GenAI #deeplearning #ChatGPT #OpenAI #SQL #python #AI #ML

Confidence intervals are widely used yet poorly understood! Today, I will clearly explain the meaning behind the "95" in a "95% confidence interval." Before we dive into formal definitions and mathematics, let's first understand what a confidence interval is and why it is necessary. Suppose you want to estimate the average weight of all the individuals in your town. You can't weigh every single person, but you can weigh a random sample. So, what you do is you pick a random sample of 50 individuals and find their average weight. Let's say the value comes out to be 70 Kgs. But this is just sample mean, how do we estimate the population mean❓ Well you can not exactly estimate the population mean! However, you can estimate aN interval around the sample mean in which the population mean would lie, this interval is what we call as the confidence interval. While estimating this interval you also chose a confidence level: Common choices are 90%, 95%, and 99%. The confidence level represents how confident we are that the interval will contain the true population mean. Here's how it's done👇 Now we come to the second part & understand what 95% Confidence Actually Mean❓ The statement "we are 95% confident that the interval contains the true population parameter" does not mean that there is a 95% probability that the true parameter lies within the interval. This is a common misconception. If you were to repeat the sample collection many times, each time calculating a 95% confidence interval for the average weight of individuals. You'd expect about 95% of those intervals to contain the true population average. The other 5% of the time, you would expect the interval to miss the true average. 🔸Let's go back to our example: You take a sample and calculate a 95% confidence interval for the average weight of individuals to be [67, 75] Kgs. Someone else takes another sample and finds a different 95% confidence interval, say [66, 74] Kgs. If this process is repeated many times, each time producing a new 95% confidence interval. In the long run, you would expect about 95% of these intervals to contain the true average weight of the individuals, and about 5% to miss it. Here's the true representation of confidence interval, the picture below shows what is true meaning of 50% confidence interval👇 If you Enjoyed reading this & are interested in - ML/MLOps 🛠 - Maths for ML 📊 - CV/NLP 🗣 - LLMs 🧠 Find me → @akshay_pachaar ✔️ Every week I do a deep dive on one of these topics! You can read this article & more with access to code in my FREE newsletter @ML_Spring! Link in the next tweet! Thanks for reading!🥂

Success! Just solved Matching Anything But a Newline on @HackerRank. Can you complete the challenge? hr.gs/caeeac #programming

Proud to be part of a worldwide family of machine learning enthusiasts! 🌍🤖 #MachineLearning #GlobalCommunity #unify.ai

Find me!

Huuuge honour to be accepted into the first ever @IntelIgnite London batch 😍 🎉 @intel shares our vision for unified AI 🟢, with great initiatives like OpenVINO and OneAPI. We're incredibly excited to now be working with some of the engineers behind these great tools 🧑‍💻, as we work together towards a more unified and efficient AI landscape 💪 We'll soon be releasing benchmarks showing how Ivy can accelerate any AI model, for unmatched runtime performance ⚡ Stay tuned 👀 In the meantime, feel free to get involved, and let's unify.ai! 🚀 ☺️

How can make progress towards a quantitative theory of the generalization behavior of neural networks? We sat down with Jamie Simon in our recent episode to discuss a working theory of the generalization of wide neural nets. Tune in here: tinyurl.com/ysftfnfu

@kanjun on how to make AI safe and accessible:

🔮✨ Embark on a coding odyssey with "CodeCraft Enchanter" – an AI sorcerer that turns bugs into butterflies and code into art. Let it be your guide, your muse, and your secret to coding magic. 🧙‍♂️🎩 #BitoCodeChallenge @BitoHQ

🎉 Excited to achieve "Advanced AI and ML Certificate"! 🔥 Ready to innovate and make a positive impact! #AI #ML #Certification 🚀🌟

🎉 Excited to announce that I've successfully completed the Python 101 Data Science Certification! 🐍📊I can't wait to apply my newfound skills to real-world projects. #DataScience #Python #Certification #LearningNeverStops 🚀📚

Excited to announce that I've earned this certificate! 🎓 #AchievementUnlocked #DeepLearning #MachineLearning

Excited to announce that I've earned this certificate! 🎓 #AchievementUnlocked

🚀 Excited to achieve the "Accelerating Deep Learning with GPUs" certification! 🔥 Grateful for the knowledge gained and endless possibilities ahead. Let's push the boundaries of AI together! #DeepLearning #GPU #Certification #AI 🚀🔍

Today a 120B model called “Galactica” is open-sourced by @paperswithcode. It’s capable of writing math notations, citations, code, chemical formula, DNA, etc. Here’s why I think Galactica is a huge milestone in open foundation models, scientific automation, and responsible AI: 🧵

Read about the research at: arxiv.org/abs/2211.09085