Building Machines That Learn and Think Like People · HackerPapers discussions

Building Machines That Learn and Think Like People — HN submission

Thu, 02 Apr 2020 04:21:45 GMT

Building Machines That Learn and Think Like People

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by taliesinb

Sun, 02 Jun 2019 15:21:11 GMT

It depends how those symbols are encoded. Techniques like attention, and systems like transformers that are built on top of them, are often produce highly interpretable execution traces simply because their patterns of activity are very revealing of how they are going about solving the task. It's harder to interrogate their learned weights in any free-standing way, of course. But the neuro-symbolic concept learning paper I gave already shows the potential translucency of these kinds of hybrid systems: the linguistic interface (its a VQA task) allows one to simply look up the feature vectors…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by areoform

Sun, 19 May 2019 21:46:54 GMT

I have made this prediction multiple times throughout the last 8 years based on my knowledge of robotics. I have argued with family members who are VCs as well as enthusiastic technical observers based on simple first principles reasoning. It is highly unlikely that completely autonomous vehicles will be present on the streets - interacting with humans, cars, and random events in real-time - within the next decade. What is more feasible and likely to occur is that large chunks of trucking may become "automated" in the form of a hyper-advanced cruise control, but these vehicles will lack Level…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Sun, 28 Jan 2018 03:29:12 GMT

Building Machines That Learn and Think Like People

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by eli_gottlieb

Mon, 24 Jul 2017 00:43:12 GMT

Counterfactuals in Pearl's sense are what allow particular models to be causal: to represent cause and effect under intervention, as opposed to mere correlation. This is an important part of how to build models that think like people[1]. [1] https://arxiv.org/abs/1604.00289

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by eli_gottlieb

Mon, 24 Apr 2017 18:22:48 GMT

Hey guys, I found the non-crappy papers: https://arxiv.org/abs/1604.00289 -- Building Machines that Learn and Think like People http://rsif.royalsocietypublishing.org/content/13/122/201606... -- Active Inference and Robot Control: a case-study

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by colorincorrect

Mon, 03 Apr 2017 06:52:05 GMT

Its very hard to say as no one can really predict when a research drought will come unless you actually do the research. Though I must say that most of the ML researchers I've come across aren't directly concerned with AGI. (either they outright dont care, or they think its a step by step thing) If AI winter comes it's probably because of disappointment of progress due to misunderstanding/misalignment with the general public / rich investors, so now you know who to blame. The state of cognitive science right now is basically a bunch of scientists saying: "yeah to be honest I have no idea…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Fri, 10 Feb 2017 23:40:20 GMT

Building Machines That Learn and Think Like People

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by pinouchon

Wed, 01 Feb 2017 23:29:15 GMT

I'd say that causality seems useful for intelligence. Josh Tenenbaum has pushed the idea of causal models and inference, and I find it compelling > Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by Cybiote

Fri, 19 Aug 2016 18:33:40 GMT

Some of these functions are easy to compose to get something impressive, true. But that is not often the case. Take the case for games and imagine we wanted a meta-algorithm to select an algorithm to apply to each game. The intelligence would then shift into, how does one select the correct algorithm for the current game in the shortest time possible? There was a recent blog post covering this and the difficulties involved: http://togelius.blogspot.ca/2016/08/algorithms-that-select-w... I also posted a link (https://arxiv.org/pdf/1604.00289v2.pdf) above which is an easily readable exposition…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by Cybiote

Fri, 19 Aug 2016 15:47:12 GMT

> Atari games just from the raw pixels on the screen It's important to distinguish between what sorts of games work well under this method and what sorts do not. Games that are variations of pole balancing, like Pong, fare better than more complex games like Asteroids, Frostbite or Montezuma's Revenge. > Saying that AlphaGo is limited because it only knows to play one game, is like saying that humans are limited because Lee Sedol could only master at world level one game. It's nothing of the sort. AlphaGo is a machine in the Turing sense. The neural network is a program that is the result of…

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — mentioned by ansible

Fri, 19 Aug 2016 10:11:38 GMT

This difference is due to deep learning not being able to build models. Check out the recent paper "Building Machines That Learn and Think Like People": https://arxiv.org/abs/1604.00289 Humans can see one or a few examples of a novel object, such as a cat, and create a fully 3D mental model of it. So we know what it will look like in different orientations and lighting conditions.

Paper and discussion history. A mention is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Sat, 30 Jul 2016 22:38:01 GMT

Building Machines That Learn and Think Like People

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Tue, 05 Apr 2016 00:24:01 GMT

Building Machines That Learn and Think Like People

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Mon, 04 Apr 2016 15:42:23 GMT

Building Machines That Learn and Think Like People

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Building Machines That Learn and Think Like People — HN submission

Mon, 04 Apr 2016 07:38:29 GMT

Building machines that learn and think like people

16 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.