SingularityNET: New Brain Simulator II Open Source Software – Charles Simon

The AGI Society has organised its 13th Artificial General Intelligence Conference this year online. The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of […]

SingularityNET: Dr. Ben Goertzel: Exploring the power of Decentralized AI | The Rise of AI Conference (2019)

How do we enable decentralised control of AI, and ultimately AGI? In his presentation at the 2019 Rise of AI Conference, Dr. Goertzel presents SingularityNET’s approach to mustering the power of decentralized AI and connecting the centralised, corporate world to open source, decentralised technology. —- SingularityNET is a decentralized marketplace for artificial intelligence. We aim […]

Exploring the FastAI Tooling Ecosystem with Hamel Husain – #532

Today we’re joined by Hamel Husain, Staff Machine Learning Engineer at GitHub. Over the last few years, Hamel has had the opportunity to work on some of the most popular open source projects in the ML world, including fast.ai, nbdev, fastpages, and fastcore, just to name a few. In our conversation with Hamel, we discuss […]

Directions in ML: “Neural architecture search: Coming of age”

Neural Architecture Search (NAS) is a very promising but still young field. I will start this talk by discussing various works aiming to build a scientific community around NAS, including benchmarks, best practices, and open source frameworks. Then, I will discuss several exciting directions for the field: (1) a broad range of possible speedup techniques […]

Explainable AI for Science and Medicine

Understanding why a machine learning model makes a certain prediction can be as crucial as the prediction’s accuracy in many applications. Here l will present a unified approach to explain the output of any machine learning model. It connects game theory with local explanations, uniting many previous methods. I will then focus specifically on tree-based […]

Detectron2: A PyTorch-based modular object detection library

Since its release in 2018, the Detectron object detection platform has become one of Facebook AI Research (FAIR)’s most widely adopted open source projects. To build on and advance this project, we are now sharing the second generation of the library, with important enhancements for both research and production use. This video shows different types […]

Building 3D deep learning models with PyTorch3D

In the same way that Torchvision and Detectron2 offer highly optimized libraries for 2D computer vision, PyTorch3D offers capabilities that support 3D data. Our open source library for 3D deep learning includes support for easy batching of heterogeneous meshes and point clouds, optimized implementations of common 3D operators such as Chamfer Loss and Graph Conv, […]

Getting involved in the TensorFlow community (TF World '19)

Large scale open source projects can be daunting, and we want TensorFlow to be accessible to many contributors. In this talk, we will outline some great ways to get involved in TensorFlow, explain how its design and development works. Presented by: Joana Carrasqueira, Nicole Pang View the website → https://goo.gle/36smBfW #TFWorld All Sessions → https://goo.gle/TFWorld19 […]

Women in ML Symposium 2021: Women in Machine Learning Symposium 2021 Livestream •

The Women in ML Symposium is a safe space for women and gendered minorities to come together and speak freely about career development through knowledge sharing and networking. Everyone is welcome to attend! This event focuses on empowering women to advance their careers, join open source communities, seek out leadership opportunities, and how we all […]

Open Source Collaboration (TensorFlow Dev Summit 2018)

Edd Wilder-James announces a new set of mailing lists to help communication and coordination, the expansion of the SIG program (Build, Swift, JavaScript, TensorBoard and Rust), and previews the public RFC process (to come in April/May 2018). TensorFlow Dev Summit 2018 All Sessions playlist → https://goo.gl/Lsaq1R Subscribe to the TensorFlow channel → https://goo.gl/ht3WGe event: TensorFlow […]

Buy AND Build for Production Machine Learning with Nir Bar-Lev – #488

Today we’re joined by Nir Bar-Lev, co-founder and CEO of ClearML. In our conversation with Nir, we explore how his view of the wide vs deep machine learning platforms paradox has changed and evolved over time, how companies should think about building vs buying and integration, and his thoughts on why experiment management has become […]

TensorFlow – the deep learning solution for mobile platforms (TensorFlow Meets)

In this episode of TensorFlow Meets, Laurence Moroney sits down to chat with Pete Warden, Tech Lead for TensorFlow on Mobile. They discuss the benefits of taking the framework of TensorFlow and fitting it down for mobile application. Watch to learn more about TensorFlow Lite, TensorFlow on Raspberry Pi, and even something for beginners- TensorFlow […]

TensorFlow Open Source Community And Collaboration (TF Dev Summit '19)

TensorFlow is where it is today because of many amazing open source contributions, through GitHub, Special Interest Groups and Requests for Comment (RFCs). In addition to that, we have communities of contributors focused on documentation, and on testing the forthcoming TensorFlow 2.0 release. This talk highlights the work of those groups, and explains how you […]

Easily deploy TF Lite models to the web | Demo

Learn to bridge the gap between mobile and web machine learning (ML) development by deploying a compatible task library TensorFlow Lite model to the web with WebAssembly. We show how it can be done with a couple of lines of code. This supports image classification, image segmentation, object detection, and text classification use cases. Resources: […]

Building a sustainable, open source machine learning platform for everyone (TensorFlow Meets)

TensorFlow is a truly open source platform with over 1,900 contributors. On this episode of TensorFlow Meets, Laurence (@lmoroney) talks to Open Source Strategist Edd Wilder-James (@edd) about how things like TensorFlow’s Request for Comments process, Special Interest Groups, and the modularity of its codebase make it easier for the community to build TensorFlow together. […]

TFX: an end-to-end machine learning platform for TensorFlow (TensorFlow Meets)

Meet Clemens Mewald, Product Manager who works on TensorFlow Extended (TFX). Watch to learn about what exactly TFX is and how it helps developers trying to deploy machine learning models in production. Clemens also talks to Laurence about the open source TensorFlow model analysis library, TF Serving, and about the possibility of a REST API. […]

At the intersection of TensorFlow & nuclear physics (TensorFlow Meets)

How does TensorFlow apply to nuclear physics? Find out in this episode of TensorFlow Meets, as Laurence chats with TensorFlow Software Engineer, Ian Langmore. Learn about power generated from nuclear fusion, new plasma generator machines, and how TensorFlow is helping with plasma measurement. Subscribe to the TensorFlow channel to stay up to date with Google’s […]

Train TensorFlow models at cloud scale with TensorFlow Cloud | Demo

What if you could instantly scale your TensorFlow model training from your local environment to take advantage of cloud-scale compute and train a bigger/faster model? Or you could do concurrent hyper-parameter training to more quickly optimize your model for your next Kaggle competition? With tensorflow_cloud, you can! Learn how to get set up and started. […]

Scaling Jupyter Notebooks with Luciano Resende – TWiML Talk #261

Today we kick off PyDataSci with Luciano Resende, an Open Source AI Platform Architect at IBM and part of the Center for Open Source Data and AI Technology. Luciano and I caught up to discuss his work on Jupyter Enterprise Gateway, a scalable way to share Jupyter notebooks and other resources in an enterprise environment. […]

TensorFlow Lite for on-device ML (TensorFlow Meets)

TensorFlow Lite is an open source deep learning framework for on-device inference, allowing you to deploy machine learning models on mobile and IoT devices. On this episode of TensorFlow Meets, Laurence (@lmoroney) talks with TF Lite Engineering Lead Raziel Alvarez about how TensorFlow Lite aims to enable the next generation of AI-based applications. Raziel’s TF […]

TensorFlow Hub for real world impact | Session

TensorFlow (TF) Hub is an open source repository of trained machine learning models. In this Session, we show how you can use TF Hub to explore and understand models to build ML solutions with real world impact. We highlight real applications, including using audio models to detect poachers in Africa, and use multilingual models for […]

Scaling Deep Learning on Kubernetes at OpenAI with Christopher Berner – TWiML Talk #199

In this episode of our AI Platforms series we’re joined by OpenAI’s Head of Infrastructure, Christopher Berner. Chris has played a key role in overhauling OpenAI’s deep learning infrastructure of the course of his two years with the company. In our conversation, we discuss the evolution of OpenAI’s deep learning platform, the core principles which […]