Learning from a few examples and generalizing to markedly different situations are capabilities of human visual intelligence that are yet to be matched by leading machine learning models. By drawing inspiration from systems neuroscience, we introduce a probabilistic generative model for vision in which message-passing-based inference handles recognition, segmentation, and reasoning in a unified way. The model demonstrates excellent generalization and occlusion-reasoning capabilities and outperforms deep neural networks on a challenging scene text recognition benchmark while being 300-fold more data efficient. In addition, the model fundamentally breaks the defense of modern text-based CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) by generatively segmenting characters without CAPTCHA-specific heuristics. Our model emphasizes aspects such as data efficiency and compositionality that may be important in the path toward general artificial intelligence.

Understanding the information processing roles of cortical circuits is an outstanding problem in neuroscience and artificial intelligence. Theory-driven efforts will be required to tease apart the functional logic of cortical circuits from the vast amounts of experimental data on cortical connectivity and physiology. Although the theoretical setting of Bayesian inference has been suggested as a framework for understanding cortical computation, making precise and falsifiable biological mappings need models that tackle the challenge of real world tasks. Based on a recent generative model, Recursive Cortical Networks, that demonstrated excellent performance on visual task benchmarks, we derive a family of anatomically instantiated and functional cortical circuit models. Efficient inference and generalization guided the representational choices in the original computational model. The cortical circuit model is derived by systematically comparing the computational requirements of this model with known anatomical constraints. The derived model suggests precise functional roles for the feed-forward, feedback, and lateral connections observed in different laminae and columns, assigns a computational role for the path through the thalamus, predicts the interactions between blobs and inter-blobs, and offers an algorithmic explanation for the innate inter-laminar connectivity between clonal neurons within a cortical column. The model also explains several visual phenomena, including the subjective contour effect, and neon-color spreading effect, with circuit-level precision. Our work paves a new path forward in understanding the logic of cortical and thalamic circuits.

Software and supplementary material is available from http://lehrach.com/wolfgang/dmf.

Summary.  The traditional approach to phylogenetic inference assumes that a single phylogenetic tree can represent the relationships and divergence between the taxa. However, taxa sequences exhibit varying levels of conservation, e.g. because of regulatory elements and active binding sites. Also, certain bacteria and viruses undergo interspecific recombination, where different strains exchange or transfer DNA subsequences, leading to a tree topology change. We propose a phylogenetic factorial hidden Markov model to detect recombination and rate variation simultaneously. This is applied to two DNA sequence alignments: one bacterial (Neisseria) and another of type 1 human immunodeficiency virus. Inference is carried out in the Bayesian framework, using reversible jump Markov chain Monte Carlo sampling.