PyTorch3d is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data. For this reason, all operators in PyTorch3d:
- Are implemented using PyTorch tensors
- Can handle minibatches of hetereogenous data
- Can be differentiated
- Can utilize GPUs for acceleration
Get started with tutorials on deforming a sphere mesh into a dolphin, rendering textured meshes, camera position optimization, and more.
Here’s a new acronym for you: Generative Teaching Networks (GTN)
GTNs are deep neural networks that generate data and/or training environments on which a learner (e.g., a freshly initialized neural network) trains before being tested on a target task (e.g., recognizing objects in images). One advantage of this approach is that GTNs can produce synthetic data that enables other neural networks to learn faster than when training on real data. That allowed us to search for new neural network architectures nine times faster than when using real data.
Fake data, real results? Sounds pretty slick.
Show us humans a picture of someone in uniform on a mound of dirt throwing a ball and we will quickly tell you we’re looking at baseball. But how do you make a computer come to the same conclusion?
In this post, we’ll explore basic methods for performing VQA and build our own simple implementation in Python
Congrats to Clément and the Hugging Face team on this milestone!
The company first built a mobile app that let you chat with an artificial BFF, a sort of chatbot for bored teenagers. More recently, the startup released an open-source library for natural language processing applications. And that library has been massively successful.
The library mentioned is called Transformers, which is dubbed as ‘state-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.’
If any of these things ring a bell to you, it may be because Practical AI co-host Daniel Whitenack has been a huge supporter of Hugging Face for a long time and mentions them often on the show. We even had Clément on the show back in March of this year.
Style-based GAN architecture produces impressive image generation results, but it’s not without its limitations. NVidia’s research team has been hard at work fixing some of the problems with StyleGAN (artifacts).
In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably detect if an image is generated by a particular network.
I love everything about this: the creativity, the engineering, the relentless desire to be as lazy as humanly possible. Chris automated 100% of this process, from content creation to social interactions to the sales pitch. A must-read.
Imagine an infinitely generated world that you could explore endlessly, continually finding entirely new content and adventures. What if you could also choose any action you can think of instead of being limited by the imagination of the developers who created the game?
WIRED’s business unit interviewed Jerome Pesenti, VP of artificial intelligence at Facebook. The major takeaway:
[he] is encouraged by progress in artificial intelligence, but sees the limits of the current approach to deep learning.
Could this be the beginning of the end for this particular AI hype cycle?
This booklet covers four main steps of designing a machine learning system:
- Project setup
- Data pipeline
- Modeling: selecting, training, and debugging
- Serving: testing, deploying, and maintaining
It comes with links to practical resources that explain each aspect in more details. It also suggests case studies written by machine learning engineers at major tech companies who have deployed machine learning systems to solve real-world problems.
This is a short introduction on methods that use neural networks in an offensive manner (bug hunting, shellcode obfuscation, etc.) and how to exploit neural networks found in the wild (information extraction, malware injection, backdooring, etc.).
Winner of Mozilla’s $50,000 award for art and advocacy exploring AI.
Stealing Ur Feelings is an augmented reality experience that reveals how your favorite apps can use facial emotion recognition technology to make decisions about your life, promote inequalities, and even destabilize American democracy. Using the AI techniques described in corporate patents, Stealing Ur Feelings learns your deepest secrets just by analyzing your face.
If you haven’t tried this yet, drop what you’re doing and give it a go. Top notch production.
Colin Lecher reporting for The Verge:
Last week, Gov. Gavin Newsom signed into law AB 730, which makes it a crime to distribute audio or video that gives a false, damaging impression of a politician’s words or actions.
While the word “deepfake” doesn’t appear in the legislation, the bill clearly takes aim at doctored works. Lawmakers have raised concerns recently that distorted deepfake videos, like a slowed video of House Speaker Nancy Pelosi that appeared over the summer, could be used to influence elections in the future.
This is the first (but likely not the last) piece of legislation aimed at fighting the potential impact of GANs Gone Wild.
It’ll be interesting to watch this game play out. I think the only long-term, sustainable solution will emerge from the same arena where the problem began: technological advances.
Folks have been talking about TensorFlow 2 for some time now (See Practical AI #42 for one excellent example), but now it’s finally here. The bulleted list:
- Easy model building with Keras and eager execution.
- Robust model deployment in production on any platform.
- Powerful experimentation for research.
- API simplification by reducing duplication and removing deprecated endpoints.
This is a huge release. Check out the highlights list in the changelog to see for yourself.
RAPIDS.ai, for the uninitiated, is a data science framework that lets you execute entirely on GPUs.
Straight from the horse’s mouth:
We’re partnering to develop a hardware and software platform within Microsoft Azure which will scale to AGI. We’ll jointly develop new Azure AI supercomputing technologies, and Microsoft will become our exclusive cloud provider—so we’ll be working hard together to further extend Microsoft Azure’s capabilities in large-scale AI systems.
Sometimes it’s hard to see the value traded in large scale investments like these. What do both sides get? With this particular investment, however, it’s pretty obvious what Microsoft is getting (Azure++) and what OpenAI is getting (an expanded R&D budget). It’s also worth noting that this is specifically focused on Artificial General Intelligence, not merely advancing the current state of the art in Machine Learning.
Sergio De Simone, reporting for InfoQ:
In a recent paper, MIT researchers introduced Gen, a general-purpose probabilistic language based on Julia that aims to allow users to express models and create inference algorithms using high-level programming constructs.
The latest machine learning research from my friends at Fast Forward Labs. Shiou Lin Sam and Nisha Muktewar teach us what meta-learners are and how they learn.
The report focuses on 5 questions about the internet.
- Is it safe?
- How open is it?
- Who is welcome?
- Who can succeed?
- Who controls it?
The answer is complicated, and the report doesn’t make any particular conclusions so much as share a series of research & stories about each topic. Includes some fascinating looks at what’s going on in AI, inclusive design, open source, decentralization and more.
On Practical AI #41, Adam Berenzweig gave a sweeping history of human-computer interaction (HCI) and a glimpse into what the future might hold.
Google, Intel, and others have recently been targeting AI at the edge with things like Coral and the Neural Compute Stick, but NVIDIA is taking things a step farther. They just announced the Jetson Nano, which is a $99 computer with 472 GFLOPS of compute performance, an integrated NVIDIA GPU, and a Raspberry Pi form factor. According to NVIDIA:
The compute performance, compact footprint, and flexibility of Jetson Nano brings endless possibilities to developers for creating AI-powered devices and embedded systems.
And it’s not only for inference (which is the main target of things like Intel’s NCS). The Jetson Nano can also handle AI model training:
since Jetson Nano can run the full training frameworks like TensorFlow, PyTorch, and Caffe, it’s also able to re-train with transfer learning for those who may not have access to another dedicated training machine and are willing to wait longer for results.
Check it out! You can pre-order now.
China has committed to becoming the world leader in AI by 2030, with goals to build a domestic artificial intelligence industry worth nearly $150 billion (according to this CNN article). Prompted by these efforts, the Semantic Scholar team at the Allen AI Institute analyzed over two million academic AI papers published through the end of 2018. This analysis revealed the following:
Our analysis shows that China has already surpassed the US in published AI papers. If current trends continue, China is poised to overtake the US in the most-cited 50% of papers this year, in the most-cited 10% of papers next year, and in the 1% of most-cited papers by 2025. Citation counts are a lagging indicator of impact, so our results may understate the rising impact of AI research originating in China.
They also emphasize that US actions are making it difficult to recruit and retain foreign students and scholars, and these difficulties are likely to exacerbate the trend towards Chinese supremacy in AI research.
OpenAI, one of the largest and most influential AI research entities, was originally a non-profit. However, they just announced that they are creating a “capped-profit” entity, OpenAI LP. This capped-profit entity will supposedly help them accomplish their mission of building artificial general intelligence (AGI):
We want to increase our ability to raise capital while still serving our mission, and no pre-existing legal structure we know of strikes the right balance. Our solution is to create OpenAI LP as a hybrid of a for-profit and nonprofit—which we are calling a “capped-profit” company.
The fundamental idea of OpenAI LP is that investors and employees can get a capped return if we succeed at our mission, which allows us to raise investment capital and attract employees with startup-like equity. But any returns beyond that amount—and if we are successful, we expect to generate orders of magnitude more value than we’d owe to people who invest in or work at OpenAI LP—are owned by the original OpenAI Nonprofit entity.
To some this makes total sense. Others have criticized the move, because they say that it misrepresents money as the only barrier to AGI or implies that OpenAI will develop it in a vacuum. What do you think?
Learn more about OpenAI’s mission from one of it’s founders in this episode of Practical AI.
Eventually Artificial Intelligence will take over the human powered content moderation jobs for Facebook. Until then, this small population of humans employed by Cognizant (on behalf of Facebook) in Phoenix, Arizona accept the job of subjecting themselves to the worst of humankind to provide “a better Facebook experience.”
Casey Newton writes for The Verge:
The video depicts a man being murdered. Someone is stabbing him, dozens of times, while he screams and begs for his life. Chloe’s job is to tell the room whether this post should be removed. She knows that section 13 of the Facebook community standards prohibits videos that depict the murder of one or more people. When Chloe explains this to the class, she hears her voice shaking.
Returning to her seat, Chloe feels an overpowering urge to sob. Another trainee has gone up to review the next post, but Chloe cannot concentrate. She leaves the room, and begins to cry so hard that she has trouble breathing.
No one tries to comfort her. This is the job she was hired to do…