https://www.newworldai.com/deep-learning-disentangled-representations-higher-level-cognition/ Artificial Intelligence, Deep Learning, Machine Learning, AI Lectures, AI Conferences, AI TED Talks, AI Movies, AI Books Tue, 03 Aug 2021 12:46:01 +0000 hourly 1 https://wordpress.org/?v=6.1.6 https://www.newworldai.com/deep-learning-disentangled-representations-higher-level-cognition/#comment-6254 Wed, 14 Feb 2018 19:10:51 +0000 http://www.artificialbrain.xyz/?p=4419#comment-6254 Unsupervised learning is solved. You need to build a neural network that is causal, calculate the action functional, and minimize it. You get the patterns directly. There are no synaptic weights, not back-propagation, no limits on depth or width. The network represents a causal set. Learning and knowledge integration are simple aggregation of causal pairs. The network grows as it learns. The causal set has mathematical properties that solve problems: adaptation, compression, continuous learning, self-explanation, one-shot learning, multiple domains and multiple sensors, invariant hierarchies, connect the dots, and many more. There are papers published, and several posts on Facebook group Not Only Deep Learning (NoDL).

]]>