@pratikac Profile picture

Pratik Chaudhari

@pratikac

Assistant professor at the University of Pennsylvania; computer scientist and roboticist

Similar User
Kaiyu Yang photo

@KaiyuYang4

Pavel Izmailov photo

@Pavel_Izmailov

Arthur Mensch photo

@arthurmensch

Stefano Ermon photo

@StefanoErmon

Sham Kakade photo

@ShamKakade6

Penn Electrical and Systems Engineering photo

@ESEatPenn

Aditya Grover photo

@adityagrover_

Nan Jiang photo

@nanjiang_cs

Pulkit Agrawal photo

@pulkitology

Kostas Daniilidis photo

@KostasPenn

will grathwohl photo

@wgrathwohl

Dinesh Jayaraman photo

@dineshjayaraman

Simon Shaolei Du photo

@SimonShaoleiDu

Yuandong Tian photo

@tydsh

RL Theory Virtual Seminars photo

@RLtheory

Pratik Chaudhari Reposted

We are proud that our online graduate students have the opportunity to study under Professor Pratik Chaudhari through his Principles of Deep Learning course. Learn more about @pratikac, the courses he teaches & his groundbreaking research: bit.ly/4aESWQZ #PennEngOnline

Pratik Chaudhari, from @ESEatPenn and @GRASPlab, aims to discover the principles that underlie learning in both AI and biological systems. Learn more about @pratikac's work and teaching in AI: bit.ly/4aESWQZ #AIMonthatPenn



Pratik Chaudhari Reposted

Pratik Chaudhari, from @ESEatPenn and @GRASPlab, aims to discover the principles that underlie learning in both AI and biological systems. Learn more about @pratikac's work and teaching in AI: bit.ly/4aESWQZ #AIMonthatPenn


Pratik Chaudhari Reposted

In a new study, members of @PennSAS and @PennEngineers found that all neural networks, the systems leading AI, follow the same route from ignorance to truth when presented with images to classify. bit.ly/3TDmFTs


Pratik Chaudhari Reposted

“Suppose the task is to identify pictures of cats and dogs, you might use the whiskers to classify them, while another person might use the shape of the ears..." Interested in the snippet from @pratikac? Read more here! grasp.upenn.edu/news/the-hidde… #GRASP #GRASPLab


Pratik Chaudhari Reposted

Our team at AWS is *hiring* interns and full-time researchers! @yaoliucs, @pratikac, I, and others work on RL, alignment, large models, and ML in general. If you have a strong relevant publications in those areas, please fill out this form. forms.gle/5KsNZ1zyKArLF4…


Pratik Chaudhari Reposted

Budgeting Counterfactual for Offline RL Great Hall & Hall B1+B2 (level 1) #1403 Tue 12 Dec 5:15 p.m. CST — 7:15 p.m. CST neurips.cc/virtual/2023/p… joint work with @yaoliucs @pratikac 3/n


Pratik Chaudhari Reposted

Offline RL is much harder than online RL or imitation learning as it needs to solve a sequence of counterfactual reasoning problems. That often gives an error of (1+\delta)^H, where delta is the one-step divergence of policy or extrapolation of Q and H is the horizon. 1/N


Pratik Chaudhari Reposted

Predictions throughout training, hyperparams and architectures are yet again shown to be on a small manifold which means models learn their classifications outputs similarly arxiv.org/abs/2305.01604 Mao ... @pratikac #MachineLearning #enough2skim

Tweet Image 1

Pratik Chaudhari Reposted

First stride of my PhD will appear at #ICML2023 @icmlconf 💫 📜 arxiv.org/abs/2208.10967 w/ @RahulRam3sh Carey E. Priebe @pratikac @neuro_data 1/3


Pratik Chaudhari Reposted

I'm very excited to announce our #CVPR2023 ✨highlight✨ paper "Beyond mAP: Towards better evaluation of instance segmentation" Project page: jenaroh.it/beyond-map/ Arxiv: arxiv.org/abs/2207.01614 Code: github.com/rohitrango/bey… A 🧵 twitter.com/rohitrango/sta…

Excited that our paper has been accepted at #CVPR2023 with three 5/5 reviews. So what did we do? New SOTA in some task? Quite the opposite, actually. Stay tuned! 😉 (P.S. Also it's my first @CVPR paper so I'm hella excited!!)



Pratik Chaudhari Reposted

Our workshop on 'New Frontiers in Learning, Control, and Dynamical Systems' will take place at #ICML2023. Aim: to unravel mutual relationships across these disciplines and shed light on recent parallel developments! Stay tuned for updates! frontiers4lcd.github.io

Tweet Image 1

Pratik Chaudhari Reposted

Happy to see our PNAS paper out: Bias in machine learning models can be significantly mitigated by careful training: Evidence from neuroimaging studies | Proceedings of the National Academy of Sciences pnas.org/doi/10.1073/pn…


Pratik Chaudhari Reposted

Checkout new version of D2L book. It covers RL now! @pratikac, @AsadiKavosh, and I authored the RL chapter. Please let us know your feedback! Also, huge thanks to @smolix, @astonzhangAZ, @zacharylipton, @mli65 for their guidance and help. Stay tuned for more topics in RL!

Our deep learning book goes 1.0 beta🎉 📕Forthcoming on Cambridge Univ Press (w @PyTorch) 🆕JAX implementation 🆕Reinforcement Learning 🆕Gaussian Processes 🆕Hyperparameter Optimization - Thank 500 contributors & 400 univs for choosing! - Free at D2L.ai (1/5)

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4


Pratik Chaudhari Reposted

I'll be at #NeurIPS2022 with Malsha from next Thu onwards! I am interested in OOD generalization, robustness to distribution shifts, and causal representation learning Eager to meet, chat, and catch up! (feel free to DM) I'm also looking for internships for next summer 🙂 1/3

Tweet Image 1

Pratik Chaudhari Reposted

Watch @pratikac seminar on Learning from small data: upenn.zoom.us/rec/share/AtLW…


Pratik Chaudhari Reposted

Does more data always help us generalize to a task when datasets contain out-of-distribution (OOD) samples? We present a counter-intuitive phenomenon arising in such circumstances arxiv.org/abs/2208.10967 w/ @AshwindeSilva1 @RahulRam3sh Carey E. Priebe @pratikac @neuro_data 1/n


Pratik Chaudhari Reposted

Assistant Professor @pratikac and team have received the @NSF CAREER Award to work on unraveling the underlying similarities between different types of learning systems with the goal of making machine learning more efficient and more widely applicable. bit.ly/3OelOEw


Pratik Chaudhari Reposted

Preview of Team Grasper's first test for our upcoming Sr. Design Demo Day on April 7th. Woohoo! #drone #engineering #tech #MondayMotivaton #university #students #education #STEM @Penn @ESEatPenn @PennEngineers


The #neurips Deep Learning through Information Geometry workshop sites.google.com/view/dl-info-n… is going on now. Join for an exciting series of talks!


Loading...

Something went wrong.


Something went wrong.