Open in app

Sign In

Write

Sign In

David Yastremsky
David Yastremsky

111 Followers

Home

About

Published in

Towards Data Science

·Pinned

Demystifying the Lottery Ticket Hypothesis in Deep Learning

Why lottery tickets are the next big thing in training neural networks — Training neural networks is expensive. OpenAI’s GPT-3 has been calculated to have a training cost of $4.6M using the lowest-cost cloud GPU on the market. It’s no wonder that Frankle and Carbin’s 2019 Lottery Ticket Hypothesis started a gold rush in research, with attention from top academic minds and tech…

Deep Learning

4 min read

Demystifying the Lottery Ticket Hypothesis in Deep Learning
Demystifying the Lottery Ticket Hypothesis in Deep Learning
Deep Learning

4 min read


Published in

Dev Genius

·Pinned

Building Your Own Search Engine From Scratch

What Underlies Modern Search? Simple Concepts. — How many times do you search the web daily? 5, 20, 50? If Google is your search engine of choice, you can look at your history of searches here. Despite how deeply search underlies our daily activities and interaction with the world, few of us understand how it works. In…

Programming

7 min read

Building Your Own Search Engine From Scratch
Building Your Own Search Engine From Scratch
Programming

7 min read


Published in

Towards Data Science

·Pinned

Exploit Your Hyperparameters: Batch Size and Learning Rate as Regularization

Rethinking these hyperparameters will improve your model’s real-world performance — Gradient descent is one of the first concepts many learn when studying machine or deep learning. This optimization algorithm underlies most of machine learning, including backpropagation in neural networks. When learning gradient descent, we learn that learning rate and batch size matter. Specifically, increasing the learning rate speeds up the…

Deep Learning

3 min read

Exploit Your Hyperparameters: Batch Size and Learning Rate as Regularization
Exploit Your Hyperparameters: Batch Size and Learning Rate as Regularization
Deep Learning

3 min read


Published in

Towards Data Science

·Mar 29, 2022

The Promise of Analog AI

Why Analog AI is About to be in Everything from Alexa to Your iPhone — Neural networks keep getting larger and more energy-intensive. As a result, the future of AI depends on making AI run more efficiently and on smaller devices. That’s why it’s alarming that progress is slowing on making AI more efficient. The most resource-intensive aspect of AI is data transfer. Transferring data…

Data Science

5 min read

The Promise of Analog AI
The Promise of Analog AI
Data Science

5 min read


Published in

Towards Data Science

·Mar 17, 2022

Making Deep Learning Climate-Friendly

How to Tackle the Carbon Footprint of AI — Deep learning is bringing many benefits to the world: solving the 50-year-old protein folding problem, detecting cancer, and improving the power grid. While there is so much that deep learning is powering, we also need to consider the costs. In the quest for more accurate and generalizable models, there has…

Deep Learning

5 min read

Making Deep Learning Climate-Friendly
Making Deep Learning Climate-Friendly
Deep Learning

5 min read


Published in

Dev Genius

·Feb 15, 2022

Two Ways to Immediately Improve Your Python Code

Two of the Most Common Mistakes Even Top Developers Make With all the talks of AI, have you ever thought about how good ol’ technology can help develop you as a software engineer? Applying software analysis tools to your code can seem tricky, yet it’s getting easier. I applied LGTM to a few public codebases to identify common mistakes. See…

Coding

3 min read

Two Ways to Immediately Improve Your Python Code
Two Ways to Immediately Improve Your Python Code
Coding

3 min read


Published in

getHealthy

·Dec 29, 2021

We Need to Discuss the Asian Flush

With This Knowledge, You Could Save a Life Living in a world where alcohol seems to permeate every social function, where being a teetotaler (person who does not drink alcohol) is a social faux pas, what do you do when you can’t drink? …

Health

3 min read

We Need to Discuss the Asian Flush
We Need to Discuss the Asian Flush
Health

3 min read


Published in

Dev Genius

·Dec 16, 2021

Your GitHub Code Could Be Better

And What To Do About It Legacy code. Technical debt. These two make up software engineers’ worst nightmares. How much exists in your repository? Learning software engineering practices usually happens in two forms: Educational content — books, courses, lectures, etc. Code reviews However, what about the gaps? Perhaps a book missed a common coding mistake or…

Software Development

2 min read

Your GitHub Code Could Be Better
Your GitHub Code Could Be Better
Software Development

2 min read


Published in

Dev Genius

·Nov 30, 2021

Pragma Once Versus Include Guards in C/C++

Save Debugging Time by Switching to #pragma once If you’ve worked with C or C++ for any non-negligible amount of time, you’ve likely run into“error: redefinition of…” To avoid this, developers often add include guards to prevent header files from being imported multiple times into one file. For example, in dog.h: #ifndef DOG_H #define DOG_H // Contents of header file #endif…

Coding

3 min read

Pragma Once Versus Include Guards in C/C++
Pragma Once Versus Include Guards in C/C++
Coding

3 min read


Published in

Dev Genius

·Oct 21, 2021

The Magic of C++ Templates and Static Variables

Unlocking the Power of Function Templates Generic programming is growing in popularity, with Golang finally scheduling generics for its 1.18 release after it being the most-desired feature for years by Go developers. By allowing your algorithms to be used across datatypes, you minimize code duplication and save yourself time. C++ is known for its compile-time optimizations…

Programming

3 min read

The Magic of C++ Templates and Static Variables
The Magic of C++ Templates and Static Variables
Programming

3 min read

David Yastremsky

David Yastremsky

111 Followers

Technologist. Dreamer. Innovator.

Following
  • Salvatore Raieli

    Salvatore Raieli

  • Diana C.

    Diana C.

  • Michael Bronstein

    Michael Bronstein

  • Anne Bonner

    Anne Bonner

  • Josh Gellers

    Josh Gellers

See all (15)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech

Teams