2022-03-12 08:11:00 CAFIAC FIX 2022-01-17 08:11:00 CAFIAC FIX 2022-01-11 08:11:00 CAFIAC FIX 2021-12-27 08:20:00 CAFIAC FIX 2021-12-12 01:34:07 Equivariance rules! https://t.co/UahEz5srF8 2021-11-26 19:31:19 RT @UofTCompSci: Join us at @UofTCompSci! We are now hiring for tenure-stream faculty positions in multiple areas. We will start reviewing… 2021-11-06 23:20:00 CAFIAC FIX 2021-11-01 19:20:00 CAFIAC FIX 2021-11-01 17:30:00 CAFIAC FIX 2021-06-26 16:21:15 A common argument against taking inspiration from the brain when designing neural networks is that it's like taking inspiration from feathers when designing flying machines. Drones need blades that will not damage things they hit and can be easily repaired with a quick preen. 2021-03-05 19:23:42 @MIT_CSAIL @StackOverflow Turning philosophy into science %Too short 2021-03-05 19:20:49 RT @MIT_CSAIL: Describe coding in exactly six words. We’ll RT all the best ones. From the folks @StackOverflow: Build. Deploy. Test. Deb… 2021-02-26 22:01:20 @rishabh16_ @hardmaru Laura Culp, Sara Sabour and I are testing the idea that the embedding vector for a part can communicate a multimodal distribution over poses and identities to the level above and the level above can disambiguate this information by combining with information at nearby locations. 2021-02-26 14:42:58 I have a new paper on how to represent part-whole hierarchies in neural networks. https://t.co/4hYb7MJ1SF 2020-12-10 16:39:42 Finding the natural parts of an object and their intrinsic coordinate frames without supervision is a crucial step in learning to parse images into part-whole hierarchies. If we start with point clouds, we can do it! https://t.co/c2cVm9yq8G 2020-11-30 20:34:13 RT @taiyasaki: Our new paper " " is out https://t.co/0t4XH4FH8H TL 2020-09-11 22:06:48 RT @A_Paccanaro: Read my latest #research on #MachineLearning applied to #DrugSideEffectsPrediction, published with @SpringerNature in @Nat… 2020-08-21 00:07:50 My wonderful former graduate student, Roland Memisevic, used neural networks to make a great fitness app: https://t.co/KYJXWHfufB 2020-08-20 17:00:12 RT @taiyasaki: Source code and full talk for : is now available – links Talk @ #ECCV2020 → h… 2020-07-23 16:56:23 RT @taiyasaki: Do you like implicit functions to model 3D geometry? We show that "Neural Articulated Shape Approximation" improves the appr… 2020-06-18 18:39:55 A non-linearity that works much better than ReLUs. The work described in this video might also be relevant to understanding grid cells. https://t.co/YlV9j79fgi 2020-06-17 18:56:19 I thought I had a very good idea about perceptual learning and accepted several invitations to give talks about it next week. But I have just discovered a fatal flaw in the idea, so I am cancelling all those talks. I apologize. 2020-06-10 20:26:26 Extrapolating the spectacular performance of GPT3 into the future suggests that the answer to life, the universe and everything is just 4.398 trillion parameters. 2020-05-26 05:41:20 @ilyasut Doing something of your own free will means the decision to do it was based on your own goals and desires. Free will is perfectly compatible with determinism. 2020-05-06 21:14:27 My friend @Jordanjacobs10 of @RadicalVCFund asked what I thought of the @covariantAI team and technology. I told him I had made a rather small investment (I don't want to reinforce reinforcement learning) but now wished I had invested 100X more. So Radical did (and then some). 2020-04-24 02:57:50 RT @taiyasaki: Do you need differentiable convex hulls? Take a look at our CvxNet work https://t.co/f784Y6xjWh https://t.co/sKRdLjXIOW 2020-04-24 02:55:29 This is a really neat way of using neural networks to get rid of polygonal meshes. The interaction of computer graphics with neural networks is really exciting. https://t.co/Gs2wRMxvkT 2020-04-24 02:51:22 RT @taiyasaki: NASA: Neural Articulated Shape Approximation Representing characters and deformable shapes without polygonal meshes for 3D… 2020-04-24 02:45:27 The sequence modeling group at the Toronto lab of Google Research has some really impressive new work on generating the words in a sequence in parallel. Imputers rock! https://t.co/QVLJiQ7zYC 2020-04-24 02:39:38 This is really nice work https://t.co/qAIJOGgL7P 2020-03-31 18:18:28 @cdavidnaylor I see that Oscar is fashion-conscious. AI (by which I mean artificial neural networks) will do many wonderful things in healthcare, but I agree that understanding the dynamics of this epidemic is a job for good old-fashioned statistical models. 2020-03-26 21:24:30 @JeffDean in another few days the corpses will outnumber the lies. 2020-03-25 02:11:24 Shooting someone on Fifth Avenue and getting away with it seems like a minor indiscretion compared with killing thousands of New Yorkers by refusing to order the manufacture of ventilators. 2020-03-24 03:12:44 I was not far off! Data from @StanfordEng Professors @yicuistanford &amp 2020-03-24 02:56:09 RT @AmyPricePhD: Data from @StanfordEng Professors @yicuistanford &amp 2020-03-23 20:24:20 Students at U. Toronto have a website https://t.co/fse8EUqAMB  for people in the Greater Toronto Area to report symptoms of COVID-19. The reported numbers of likely positive cases and vulnerable individuals are displayed for each region defined by the first half of the postcode. 2020-03-16 23:20:32 I have one N95 mask. After using, I put it in a plastic bag, wash my hands and bake at 170F for 2 hours. My guess is that a half-baked mask is better than none. I would love to know whether baking at 170F reliably kills COVID-19 and whether it degrades the filtering by the mask. 2020-03-15 03:28:37 RT @tingchenai: Happy to share that we've open-sourced both the code and pretrained models for SimCLR (a simple framework for contrastive l… 2020-03-03 19:41:32 Organizers of data science and machine learning conferences (NeurIPS, ICML, AISTATS, ICLR, UAI, ...): Allow remote paper &amp 2020-02-20 20:37:07 Suppose you have cancer and you have to choose between a black box AI surgeon that cannot explain how it works but has a 90% cure rate and a human surgeon with an 80% cure rate. Do you want the AI surgeon to be illegal? 2020-02-14 22:28:38 Unsupervised learning of representations is beginning to work quite well without requiring reconstruction. https://t.co/EgZbX3tYD7 2019-11-17 02:48:58 RT @arkosiorek: We've just open-sourced the code for Stacked Capsule Autoencoders (NeurIPS '19): https://t.co/tP5FSq6dqC joint work with @… 2019-07-22 17:14:36 This is a much better version of capsules. https://t.co/h9GDx5HsrS 2019-06-23 17:37:29 RT @ylecun: This report on Trump's concentration camps for migrant children is absolutely horrifying. Conditions are unsanitary and unsafe.… 2019-04-21 02:51:59 Inman is always thought-provoking. https://t.co/pdGuMJaduS 2019-04-21 01:07:22 @ilyasut The future is already here: I trained a neural net called Ilya for 10 years :-) 2019-03-27 17:49:58 The X factor: When I was an undergrad at Kings College Cambridge, Les Valiant who won the Turing award in 2010 lived in the adjacent room on X staircase. He just told me that Turing lived on X staircase when he was a fellow at Kings and probably wrote his 1936 paper there! 2019-03-27 14:40:45 @JeffDean @ylecun @TheOfficialACM Thanks to my graduate students and postdocs whose work won a Turing award. Thanks to my visionary mentors Inman Harvey, David Rumelhart and Terry Sejnowski. And thanks to Jeff Dean for creating the brain team that turns basic research in neural nets into game-changing products. 2019-02-27 19:24:58 @aureliengeron @burkov :-) One fey thin frog 2019-02-22 21:25:02 Some new work from the brain team in Toronto @rishabh_467 @Mo_Norouzi https://t.co/aHJL9WIAHx 2019-02-14 20:35:32 @ilyasut This should allow unicorns in silicon valley to produce better English. https://t.co/NJOFuInpYa 2019-02-05 05:02:10 RT @VectorInst: Vector Institute is offering scholarships to top candidates applying to AI Master’s Programs. Learn more https://t.co/pT1j… 2019-01-22 21:21:10 @inemshan That's only my view about backpropagation when trying to understand the brain and even then I'm not sure. It would be silly to throw it away when doing engineering, because it works really well. 2019-01-16 16:51:28 @tarinziyaee :-) 2019-01-15 23:59:54 My Coursera MOOC "Neural Networks for Machine Learning" was prepared in 2012 and is now seriously out of date so I have asked them to discontinue the course. But the lectures are still a good introduction to many of the basic ideas and are available at https://t.co/HBbKhA6o8q 2019-01-14 22:26:35 The Google Brain team in Toronto has openings for several research scientists who have already made exceptional contributions to research on deep learning or its applications in NLP, vision, or reinforcement learning. To apply, go to https://t.co/fYfNjDcm5P 2001-01-01 01:01:01