Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network · HackerPapers discussions

Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network — mentioned by pakl

Thu, 09 May 2019 04:29:31 GMT

Deep convolutional networks, by design, are unable to integrate contextual and ambient information present in an image (or in preceding images) to inform how to interpret local features they use. So it's no surprise they struggle with unconstrained images. Images where ambient context varies. It's intriguing how much focus there is on adversarial examples. You don't need adversarial examples to make a deep network fail - in a sense that's overkill. Just point the poor deep network at a sequence of images from the real world -- images from a self driving car, security camera, or webcam. You'll…

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

Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network — mentioned by felippee

Wed, 07 Dec 2016 15:59:03 GMT

Hi, I'm the blogger. I just want to add a very simple statement: In order to create a model of the world, the machine learning substrate has to have the capacity to cover the observed dynamics. Hard not to agree with this, almost sounds like a tautology. Now let's try to derive conclusions: - World dynamics is full of multi-scale interactions (e.g. in vision illumination of a single pixel depends on the whole scene and the whole scene depends on many tiny details). To capture that, the machine learning substrate has to allow low level representations access high level stuff. Hence feedback…

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

Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network — mentioned by pakl

Wed, 07 Dec 2016 15:29:18 GMT

Lecun has identified a real problem for AI -- the need to understand the real world, the link between intelligence and prediction over time. But the tools he is using are not the right ones. Deep conv nets were not designed with prediction over time in mind. Here's one reason: Deep convolutional nets do not handle dynamical information from their lowest layers. By design, conv layers and pooling layers immediately begin discarding spatial information that could be used for building up predictions. In contrast it is possible to start with recurrent/feedback networks at the very first layers of…

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