Abstract — Neural networks are relatively successful in recognizing individual patterns. However, when images consist of combination of patterns, a preprocessing step of segmentation is required to avoid combinatorial explosion of the training phase. In practical applications, segmentation is a context dependent task which itself requires recognition. In this paper we propose and develop a biologically inspired neural architecture that can recognize and count an arbitrary collection of objects even if trained with individual objects, without making use of additional segmentation algorithms. The two essential features that govern the neurons in this algorithm are 1. dynamical feedback and 2. competition for activation. We show analytically that while the equations governing the output neurons are highly nonlinear in individual feature amplitudes, they are linear in groups of feature amplitudes. We further demonstrate through simulations, that our architecture can precisely count and recognize scenes in which three and four non-overlapping patterns are presented simultaneously. The ability to generalize numerosity outside the training distribution with a simple learning scheme, lack of connection weights and segmentation algorithms prove regulatory feedback networks not only beneficial for machine learning tasks but also for biological modeling of animal vision. I.

normalization using cortical strip maps:

The hippocampus participates in multiple functions, including spatial navigation, adaptive timing, and declarative (notably, episodic) memory. How does it carry out these particular functions? The present article proposes that hippocampal spatial and temporal processing are carried out by parallel circuits within entorhinal cortex, dentate gyrus, and CA3 that are variations of the same circuit design. In particular, interactions between these brain regions transform fine spatial and temporal scales into population codes that are capable of representing the much larger spatial and temporal scales that are needed to control adaptive behaviors. Previous models of adaptively timed learning propose how a spectrum of cells tuned to brief but different delays are combined and modulated by learning to create a population code for controlling goal-oriented behaviors that span hundreds of milliseconds or even seconds. Here it is proposed how projections from entorhinal grid cells can undergo a similar learning process to create hippocampal place cells that can cover a space of many meters that are needed to control navigational behaviors. The suggested homology between spatial and temporal processing may clarify how spatial and temporal information may be integrated into an episodic memory. The

continuous-distracter free recall, sensory-motor imitation, chunking, sequence learning, prefrontal cortex, parietal cortex, position coding, rank order cells, cerebral cortex, laminar computing * Authors are listed in alphabetical order. 1

All correspondence should be addressed to

How does working memory store multiple spatial positions to control sequences of eye movements, particularly when the same items repeat at multiple list positions, or ranks, during the sequence? An Item-Order-Rank model of working memory shows how rank-selective representations enable storage and recall of items that repeat at arbitrary list positions. Rankrelated activity has been observed in many areas including the posterior parietal cortices (PPC), prefrontal cortices (PFC) and supplementary eye fields (SEF). The model shows how rank information, originating in PPC, may support rank-sensitive PFC working memory representations and how SEF may select saccades stored in working memory. It also proposes how SEF may interact with downstream regions such as the frontal eye fields (FEF) during memory-guided sequential saccade tasks, and how the basal ganglia (BG) may control the flow of information. Model simulations reproduce behavioral, anatomical and electrophysiological data under multiple experimental paradigms, including visually- and memory-guided single and sequential saccade tasks. Simulations reproduce behavioral data during two SEF microstimulation paradigms, showing that their seemingly inconsistent findings about saccade latency can be reconciled.