Introducing Lightning AI

Learn how you can build in days not months with the most intuitive, flexible framework for building models and Lightning Apps (ie: ML workflow templates) which “glue” together your favorite ML lifecycle tools: https://lightning.ai/ Source of this PyTorch Lightning Video

Meet John and Rosie, fighting plastic pollution with proteins – Unfolded

It all started with an email. The world produces around 400m tonnes of plastic waste each year. Much of it ends up in landfill; a significant portion is polluting the world’s oceans. Conventional plastic recycling only degrades the material – in fact, most plastic items never fully disappear. John McGeehan, Rosie Graham, and their colleagues […]

TensorFlow Serving client examples

Wei Wei, Developer Advocate at Google, walks through how to send REST and gRPC prediction requests to TensorFlow serving backend with Python and C++. Don’t worry if your client uses another language, below there are new sets of codelabs covering web, Android, Flutter, and iOS frontends. Codelabs Image Classification with TensorFlow Serving (Web) → https://goo.gle/3tQfqMb […]

Hugging Face Train a Model (11.4)

Hugging Face transformer models can be used as a starting place to train and fine tune models of your own. This video demonstrates how to train and fine tune Hugging Face models. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_11_04_hf_train.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton Tweets by jeffheaton Support Me on Patreon: https://www.patreon.com/jeffheaton Source of this […]

How Marcelo and Megan solved a ten-year problem in minutes – Unfolded

Most people who have access to a modern healthcare system would not consider a disease like bubonic plague to be a threat. Such bacterial infections are usually dealt with easily through modern antibiotics. Yet antibiotic resistance, where bacteria evolve the ability to defeat these drugs, is fast becoming a growing global problem – and new […]

Deploying production ML models with TensorFlow Serving overview

Wei Wei, Developer Advocate at Google, overviews deploying ML models into production with TensorFlow Serving, a framework that makes it easy to serve the production ML models with low latency and high throughput. Learn how to start a TF Serving model server and send POST requests using the command line tool. Wei covers what it […]

The “spell check” of design systems – Made with TensorFlow.js

Meet Joo Hyung Park, a software engineer and product designer, from South Korea who is working on the “spell check” of design systems. His project, Figma ML, uses TensorFlow.js to go through four checkpoints to recognize key elements of UI design using a custom object detection API to determine if there are any design issues […]

SingularityNET: Rejuve.AI Longevity Townhall Meeting 1

Recording of Rejuve.AI’s public Townhall Meeting. As one of SingularityNET’s spin-off projects, Rejuve’s core mission is to build a decentralized network of researchers, clinics, and data contributors working together to arrive at breakthrough discoveries in the fight against aging, while making the resulting solutions affordable and accessible for all. Rejuve puts power back into the […]

DeepMind Makes Prototyping Papers Easy with ACME

DeepMind’s ACME framework makes implementing deep reinforcement learning agents incredibly easy. By using a modularized approach to agent design, agents can be scaled from a single thread up to hundreds easily. In this video I’ll give you a brief overview of how all the pieces fit together. Learn how to turn deep reinforcement learning papers […]

Two Minute Papers: NVIDIA’s AI Plays Minecraft After 33 Years of Training! 🤖

❤️ If you wish to support us and watch these videos in early access, check this out: – https://www.patreon.com/TwoMinutePapers 📝 The paper “MineDojo – Building Open-Ended Embodied Agents with Internet-Scale Knowledge” is available here: https://minedojo.org/ 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, […]

Equivariant Priors for Compressed Sensing with Arash Behboodi – #584

Today we’re joined by Arash Behboodi, a machine learning researcher at Qualcomm Technologies. In our conversation with Arash, we explore his paper Equivariant Priors for Compressed Sensing with Unknown Orientation, which proposes using equivariant generative models as a prior means to show that signals with unknown orientations can be recovered with iterative gradient descent on […]

Learn PyTorch for deep learning in a day. Literally.

Welcome to the most beginner-friendly place on the internet to learn PyTorch for deep learning. All code on GitHub – https://dbourke.link/pt-github Ask a question – https://dbourke.link/pt-github-discussions Read the course materials online – https://learnpytorch.io Sign up for the full course on Zero to Mastery (20+ hours more video) – https://dbourke.link/ZTMPyTorch Below are the timestamps/outline of the […]

How to find N-Largest and N-Smallest Numbers in Python!

Quick Python tip how to efficiently find the n largest or smallest numbers of a List. A note from the official docs: “The latter two functions perform best for smaller values of n. For larger values, it is more efficient to use the sorted() function. Also, when n==1, it is more efficient to use the […]

Ep10: Python Classes and Object-Oriented Programming

Learn the basic idea behind object oriented-programming in Python. Object-oriented programming is one of the essential concepts behind using Python at its full potential, and it’s one of the cornerstones of modern machine learning deep learning frameworks like scikit-learn and PyTorch. Follow Sebastian: https://twitter.com/rasbt Follow William: https://twitter.com/_willfalcon More Learning materials: https://www.pytorchlightning.ai/edu/engineering-class. Learn with the community: […]

Two Minute Papers: NVIDIA GTC: When Simulation Becomes Reality! 🤯

❤️ Check out Lambda here and sign up for their GPU Cloud: https://lambdalabs.com/papers If everything goes well, this will be my GTC talk: https://www.nvidia.com/gtc/session-catalog/?ncid=so-face-527732&tab.catalogallsessionstab=16566177511100015Kus#/session/16559245032830019Q6q ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: – https://www.patreon.com/TwoMinutePapers – https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters […]

KineCAM: An instant camera for animated paper photos

KineCAM is instant camera that takes kinegrams, which are paper photos that show animation. Originating as an MIT class project, KineCAM is made of inexpensive parts and easy to construct. For more info visit: https://news.mit.edu/2022/new-twist-old-school-animation-kinecam-0721 Or read the technical paper here: https://hcie.csail.mit.edu/research/kinecam/kinecam.html YouTube Source for this AI Video

Decarbonising cities pitching challenge | Climate

Decarbonising cities pitching competition – CogX and Shell are looking for start-ups with novel ideas on how digital technologies can provide a cleaner energy future for our cities. The three finalists are start-ups working on the next big idea that could revolutionise the way we decarbonise cities. See them pitch their solution to a jury […]

Two Minute Papers: Finally, Robotic Telekinesis is Here! 🤖

❤️ Check out Weights & Biases and sign up for a free demo here: https://wandb.com/papers ❤️ Their mentioned post is available here (thank you Soumik!): http://wandb.me/robotic-telekinesis 📝 The paper “Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube” is available here: https://robotic-telekinesis.github.io/ ❤️ Watch these videos in early access on our Patreon […]

Schedule Python Scripts with GitHub Actions FOR FREE | Python Automation

Learn how to schedule Python scripts with GitHub Actions FOR FREE in this Python Automation tutorial! 💻Starter files: https://github.com/python-engineer/python-github-action-template 🎦 Cron job Tutorial: https://youtu.be/5bTkiV_Aadc ✅ Write cleaner code with Sourcery, instant refactoring suggestions in VS Code & PyCharm: https://sourcery.ai/?utm_source=youtube&utm_campaign=pythonengineer * Get my Free NumPy Handbook: https://www.python-engineer.com/numpybook ⭐ Join Our Discord : https://discord.gg/FHMg9tKFSN 📓 ML Notebooks […]

Ep09: Collaborate on Coding Projects with GitHub

Learn how to share your code on GitHub and collaborate with others on open-source projects. William and Sebastian discuss how to collaborate with pull requests. This is a continuation of the previous episode, which is available here: https://youtu.be/_0X_dljzr5E Episode show notes: https://github.com/Lightning-AI/engineering-class/blob/main/ep09-github-collab/Ep09-ShowNotes.md Follow Sebastian: https://twitter.com/rasbt Follow William: https://twitter.com/_willfalcon More Learning materials: https://www.pytorchlightning.ai/edu/engineering-class. Learn with the […]

SingularityNET: Inside SingularityNET | July 2022

This is a recording of the #SingularityNET Ecosystem leaders meeting, from mid-July 2022, including updates on project progress, exciting news, and discussions around key initiatives. ———————- SingularityNET is the world’s leading decentralized AI platform, and the first and only blockchain protocol that allows AIs to cooperate and coordinate at scale, to form a beneficial ecosystem […]

Two Minute Papers: NVIDIA’s New AI Trained For 10 Years! But How? 🤺

❤️ Check out Weights & Biases and sign up for a free demo here: https://wandb.com/papers ❤️ Their mentioned post is available here (thank you Soumik!): http://wandb.me/ASE 📝 The paper “ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters” is available here: https://nv-tlabs.github.io/ASE/ 📝 Our material synthesis paper with the latent space is available here: […]