Work by @LittleBimble with @pfau, @pushmeet, Matko Bosnjak, Lars Buesing, Kevin Ellis, and Marek Sergot. (2/)
— DeepMind (@DeepMind) May 14, 2021
The ability to learn the world dynamics sample efficiently is a key component of intelligence, according to @MelMitchell1, @GaryMarcus, @fchollet, @mpshanahan, among many others. (4/4)
— DeepMind (@DeepMind) May 14, 2021
Abstract from the linked article:
How should a machine intelligence perform unsupervised structure discovery over streams of sensory input? One approach to this problem is to cast it as an apperception task [1]. Here, the task is to construct an explicit interpretable theory that both explains the sensory sequence and also satisfies a set of unity conditions, designed to ensure that the constituents of the theory are connected in a relational structure.
However, the original formulation of the apperception task had one fundamental limitation: it assumed the raw sensory input had already been parsed using a set of discrete categories, so that all the system had to do was receive this already-digested symbolic input, and make sense of it. But what if we don't have access to pre-parsed input? What if our sensory sequence is raw unprocessed information?
The central contribution of this paper is a neuro-symbolic framework for distilling interpretable theories out of streams of raw, unprocessed sensory experience. First, we extend the definition of the apperception task to include ambiguous (but still symbolic) input: sequences of sets of disjunctions. Next, we use a neural network to map raw sensory input to disjunctive input. Our binary neural network is encoded as a logic program, so the weights of the network and the rules of the theory can be solved jointly as a single SAT problem. This way, we are able to jointly learn how to perceive (mapping raw sensory information to concepts) and apperceive (combining concepts into declarative rules).
