Ubiquitous Intelligence, Common Sense Reasoning #knowledgeispower Tweets, Opinions my own
Noida, India
Joined July 2009
- Tweets796
- Following904
- Followers221
- Likes369
IRL Podcast: TL;DR w/ @Mozilla & @Manoushz irlpodcast.org/season4/episo…
This is so true ! :|
"– the tabs are breeding like bunnies and you can’t close them because they’re too important and interesting. So they sit there, taunting you."
Karan Verma retweeted
I was online-educated in Deep Learning. I started from @AndrewYNg's ML MOOC, Stanford tutorials, to Hinton's MOOC on Neural Networks.
I rediscovered an old blog post I wrote 4 years ago. For some reason I was so fascinated with autoencoders and … MNIST.
blog.otoro.net/2014/12/19/ma…
Karan Verma retweeted
This looks so awesome.
Our new paper learns concepts as programs on a 'visual cognitive computer', showing zero-shot task-transfer on robots, and strong generalization. We bring cogsci ideas about perceptual symbol systems and image schemas into the realm of machine learning. arxiv.org/abs/1812.02788
Karan Verma retweeted
Announcing AI For Everyone, the newest @deeplearningai_ course! Whether you're a CEO, product manager, marketer, recruiter, designer, or financier, this non-technical course will help you understand how to apply AI in your company, and navigate AI's rise. medium.com/@andrewng/announc…
Karan Verma retweeted
Releasing Spinning Up in Deep RL, a new educational package to let anyone become a deep reinforcement learning practitioner: blog.openai.com/spinning-up-…
Next year, we'll teach workshops on Spinning Up at CHAI, OpenAI, and other venues.
Karan Verma retweeted
Learning to Dress: Synthesizing Human Dressing Motion via Deep Reinforcement Learning @siggraph @SIGGRAPHAsia #siggraph
Karan Verma retweeted
I'm really impressed with the @PyTorch devcom so far. Short (10 min), technical, clear talks. There's a live-stream for those that couldn't make it: facebook.com/pytorch/videos/…
It was only two years ago that @PyTorch was released. At the time @TensorFlow was the assumed champion. @PyTorch established themselves by consistently working to solve user needs. This helped change the direction of the entire ecosystem. Thanks to all the @PyTorch community :)
ALT The first ever PyTorch Conference
Karan Verma retweeted
Just finished writing final few chapters of Machine Learning Yearning book draft, on how to organize and strategize your ML projects. Will send out soon -- sign up at mlyearning.org if you want a copy!
Karan Verma retweeted
Using Kaggle to start and guide your ML/data science journey towardsdatascience.com/use-k… – at Offaly, Ireland
Karan Verma retweeted
Technology throwback 🤓 – at Wandsworth, London
I put Windows 95 into an Electron app that now runs on macOS, Windows, and Linux. It's a terrible idea that works shockingly well. I'm so sorry.
Go grab it here: github.com/felixrieseberg/wi…
Karan Verma retweeted
My friend Dawn Song @dawnsongtweets just visited our office to film the next Heroes of Deep Learning interview. She gave a lot of inspiring advice on how to become great at DL. Video coming soon! – at Palo Alto, CA
Karan Verma retweeted
Just read this cool paper: Neural net pretraining keeps improving when you train on an unprecedented 3.5 billion (that's really big) labeled images and transfer to new task. IMO we're still nowhere near the limits of pretraining/transfer learning. research.fb.com/publications… – at Palo Alto, CA
Karan Verma retweeted
We need to build a better educated world, and I'm excited about the role that AI is playing in helping companies and individuals navigate this! @coursera @emilygsands technologyreview.com/s/61179… – at Stanford, CA
Scared? no no...THIS IS SUPER EXCITING!!! This is PROGRESS!!!!!!
@BostonDynamics @TheRegister
@RickandMorty #science #Robotics #ArtificialIntelligence theregister.co.uk/AMP/2017/1…
Karan Verma retweeted
New paper: a framework for learning interpretable first-order rules from noisy or ambiguous data. arxiv.org/abs/1711.04574 @egrefen @LittleBimble
Karan Verma retweeted
Ridiculously good looking GAN results from Karras et al. (NVIDIA) by progressively growing the network: research.nvidia.com/sites/de…
Karan Verma retweeted
It's looking like the backprop video, which I'm getting increasingly excited about, will come out next Tuesday.
Karan Verma retweeted
Hierarchical reinforcement learning algorithm that learns high-level actions which can be reused across tasks: blog.openai.com/learning-a-h…