Conversational AI w/ Jarvis – checking out the API

The Jarvis API has models for just about everything you could need for end to end conversational AI, including text to speech, speech to text, named entity recognition and a bunch more. Learn more about NVIDIA Jarvis: https://nvda.ws/2QC3NYv See more of the DGX Station A100 here: https://youtu.be/0mAesfFt4us Neural Networks from Scratch book: https://nnfs.io Channel membership: […]

Apex – Michael Carilli, NVIDIA

Apex is an open-source PyTorch extension that helps users maximize deep learning training performance on NVIDIA GPUs. Mixed precision utilities in Apex are designed to improve training speed while maintaining the accuracy and stability of training in single precision. Learn more in this talk. Source of this PyTorch AI Video

PyTorch and Keras TensorFlow for the Next 3 Years, Reflections from GTC 2021

Several presentations at GTC-21 discussed the next 3-5 year direction for PyTorch and Keras/Tensorflow. In this video, I summarize what is ahead for these important frameworks. Presentations referenced: François Chollet Soumith Chintala https://www.nvidia.com/en-us/gtc/topics/ 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 machine learning/AI Video

This is the Best Artificial Intelligence Model of 2021 – Megatron-Turing

Microsoft and Nvidia have been working hard to finally create an Artificial Intelligence Model which surpasses and beats OpenAI’s GPT3 with more than double the parameter count and almost reaching the amazing and intelligent amount of 1 Trillion Parameter models. Unless OpenAI comes out with GPT4, it seems like the Megatron-Turing NLP AI Model is […]

CoRL 2020, Spotlight Talk 187: Learning a Contact-Adaptive Controller for Robust, Efficient Legge…

“**Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion** Xingye Da (Nvidia)*; Zhaoming Xie (University of British Columbia); David Hoeller (Nvidia); Byron Boots (Nvidia); Anima Anandkumar (); Yuke Zhu (University of Texas – Austin); Buck Babich (NVIDIA); Animesh Garg (University of Toronto, Vector Institute, Nvidia) Publication: http://corlconf.github.io/paper_187/ **Abstract** We present a hierarchical framework that combines […]

Installing TensorFlow/Keras CPU/GPU w/CONDA (July, 2020)

This video shows how to set up a CONDA environment containing Keras/Tensorflow and several useful machine learning libraries. CONDA allows you to isolate the GPU drivers into a self-contained environment that greatly simplifies the installation process. The setup shown by this video is designed for my deep learning course; however, it can also serve as […]

My Journey to PyTorch by Piotr Bialecki @Nvidia | PyTorch Ecosystem Day 2021

Piotr Bialecki is the Technical Lead of The PyTorch Team @ NVIDIA, where he supports internal and external users in using PyTorch on NVIDIA GPUs. Piotr is well-known in the community for posting over 20,000 helpful comments on the PyTorch Forum (https://discuss.pytorch.org/). He opens the PyTorch Ecosystem Day 2021 EMEA/US session welcoming the community and […]

32K Mandelbrot Zooms on NVIDIA RTX A6000 48GB GPU Python

The massive amount of RAM on the NVIDIA RTX A6000 is great for generating ultra high resolution 32K images of the Mandelbrot set. In this video I show how to use TensorFlow to create both Mandelbrot images and zooms using a GPU. Unlike deep learning, which deals well with 32bit floating point, Mandelbrot zooms must […]

NVIDIA’s Image Restoration AI: Almost Perfect

The paper “Noise2Noise: Learning Image Restoration without Clean Data” and its source code are available here: 1. https://arxiv.org/abs/1803.04189 2. https://github.com/NVlabs/noise2noise 3. https://news.developer.nvidia.com/ai-can-now-fix-your-grainy-photos-by-only-looking-at-grainy-photos/ Have a look at this too, some materials are now available for download! – https://developer.nvidia.com/rtx/ngx Unofficial implementation: https://github.com/yu4u/noise2noise Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers We would like to thank our […]

Two Minute Papers: NVIDIA’s New AI Draws Images With The Speed of Thought! ⚡

❤️ Check out Cohere and sign up for free today: https://cohere.ai/papers Online demo – http://gaugan.org/gaugan2/ NVIDIA Canvas – https://www.nvidia.com/en-us/studio/canvas/ 📝 The previous paper “Semantic Image Synthesis with Spatially-Adaptive Normalization” is available here: https://nvlabs.github.io/SPADE/ 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, Alex Haro, […]

NVIDIA RTX A6000 First Look for Data Science 48GB Ampere GPU

NVIDIA was kind enough to provide an NVIDIA RTX A6000 for my YouTube channel. This amazing Ampere GPU contains 10,752 CUDA cores, 336 Tensor Cores, and 48GB of RAM! This GPU actually contains more RAM than most computer systems! In this video, I give the A6000 an initial look and show its installation into my […]

Break into AI: I took an online course, what's next?

Welcome to the virtual Learner Community Event hosted by DeepLearning.AI. We have assembled a panel of machine learning practitioners who have gotten into the field from different paths. They will be sharing their first-hand experience and suggestions on how to transition from online courses to landing your first ML job! Topics that you can expect […]

Install RAPIDS with XGBoost on an NVIDIA GPU

In this video, I show how to install and use RAPIDS/DASK with XGBoost. This allows you to use Pandas and scikit-learn type tools in a distributed system on GPUs. Code and links: https://github.com/jeffheaton/present/blob/master/youtube/nvidia/rapids.ipynb https://rapids.ai/ Lenovo P-series: https://www.lenovo.com/us/en/laptops/thinkpad/thinkpad-p/c/thinkpadp NVIDIA Quadro RTX 5000: https://www.nvidia.com/en-us/design-visualization/quadro/rtx-5000/ ** Follow Me on Social Media! GitHub: https://github.com/jeffheaton Twitter: https://twitter.com/jeffheaton Instagram: https://www.instagram.com/jeffheatondotcom/ Discord: […]

Two Minute Papers: AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215

The paper “Interactive Reconstruction of Monte Carlo Image Sequences using a Recurrent Denoising Autoencoder” is available here: http://research.nvidia.com/publication/interactive-reconstruction-monte-carlo-image-sequences-using-recurrent-denoising The paper with the notoriously difficult “Spheres” scene: Automatic Parameter Control for Metropolis Light Transport – Eurographics 2013, Short Paper – Károly Zsolnai, László Szirmay-Kalos (2013) We would like to thank our generous Patreon supporters who make […]

Is Kaggle Useful in the Real World — NVIDIA GTC 2022

Is Kaggle useful in the real world? Can Kaggle get you a job? In this video I give a quick recap of the GTC 2022 session, “Applying Lessons From Kaggle-winning Solutions to Real-world Problems [S42635]”. 1:29 Talk overview 2:09 Is Kaggle applicable to the real world? 3:08 How is Kaggle different from the real world? […]

Harri Valpola: System 2 AI and Planning in Model-Based Reinforcement Learning

In this episode of Machine Learning Street Talk, Tim Scarfe, Yannic Kilcher and Connor Shorten interviewed Harri Valpola, CEO and Founder of Curious AI. We continued our discussion of System 1 and System 2 thinking in Deep Learning, as well as miscellaneous topics around Model-based Reinforcement Learning. Dr. Valpola describes some of the challenges of […]

cuDF, cuML & RAPIDS: GPU Accelerated Data Science with Paul Mahler – TWiML Talk #254

Today we’re joined by Paul Mahler, senior data scientist and technical product manager for machine learning at NVIDIA. In our conversation, Paul and I discuss NVIDIA’s RAPIDS open source project, which aims to bring GPU acceleration to traditional data science workflows and machine learning tasks. We dig into the various subprojects like cuDF and cuML […]

AD as it relates to Differentiable Programming for ML @ TWiML Online Meetup Americas 20 March 2019

**SUBSCRIBE AND TURN ON NOTIFICATIONS** **twimlai.com** This video is a recap of our March 2019 Americas TWiML Online Meetup: Automatic Differentiation as it relates to Differentiable Programming for Machine Learning. In this month’s community segment, we discuss our upcoming April Meetups, NVIDIA’s Jetson Nano Platform, NVIDIA’s Cloud Strategy, attention in NLP, and Sam’s Kubernetes eBook. […]

Why Intel is Beating Everyone in Artificial Intelligence – Intel Loihi 2

In order to regain its lead Intel lost from AMD, Intel is now releasing several completely new revolutionary products which are meant to both beat and surpass AMD + NVIDIA in their respective fields. Intel Loihi 2 is one of the first neuromorphic computing chips ever released to consumers and is also the most powerful […]

[ML News] OpenAI removes GPT-3 waitlist | GauGAN2 is amazing | NYC regulates AI hiring tools

#mlnews #gaugan #gpt-3 Your weekly dose of ML News! More GauGAN images here: https://drive.google.com/drive/folders/1tG1rpxP_mnspB1MWi9VZGScw5R-hxUdm?usp=sharing OUTLINE: 0:00 – Intro 0:20 – Sponsor: Weights & Biases 2:20 – OpenAI’s removes GPT-3 Waitlist 4:55 – NVIDIA releases GauGAN2 Webapp 9:45 – Everyday Robots tackles real-life tasks 12:15 – MetNet-2: 12-hour Rain Forecasting 14:45 – TinyML Dog Bark Stopper […]

PyTorch Developer Day 2020 | Full Livestream

Join us for PyTorch Developer Day 2020, where we’ll look at technical talks, core updates, and project deep dives. The video will cover a variety of topics, including updates to the core framework and new tools and libraries to support development across a number of domains. You’ll also hear from the community on the latest […]

Exploring Style GAN2 Latent Vector: Controlling Facial Properties

We go inside of the latent vectors of nVidia StyleGAN2 faces. We see how we can gain some degree of control over the face being generated. I demonstrate a technique that I used to generate faces and control if they have glasses. https://github.com/jeffheaton/present/blob/master/youtube/gan_explore.ipynb My deep learning course: https://sites.wustl.edu/jeffheaton/t81-558/ Source of this machine learning/AI Video

AI-Based Video-to-Video Synthesis

The paper “Video-to-Video Synthesis” and its source code is available here: https://tcwang0509.github.io/vid2vid/ https://github.com/NVIDIA/vid2vid Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers We would like to thank our generous Patreon supporters who make Two Minute Papers possible: 313V, Andrew Melnychuk, Angelos Evripiotis, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Eric Martel, […]