A minimal synaptic architecture is proposed for how the brain might perform path integration by computing the next internal representation of self-location from the current representation and from the perceived velocity of motion. In the model, a place-cell assembly called a "chart" contains a twodimensional attractor set called an "attractor map" that can be used to represent coordinates in any arbitrary environment, once associative binding has occurred between chart locations and sensory inputs. In hippocampus, there are different spatial relations among place fields in different environments and behavioral contexts. Thus, the same units may participate in many charts, and it is shown that the number of uncorrelated charts that can be encoded in the same recurrent network is potentially quite large. According to this theory, the firing of a given place cell is primarily a cooperative effect of the activity of its neighbors on the currently active chart. Therefore, it is not particularly useful to think of place cells as encoding any particular external object or event. Because of its recurrent connections, hippocampal field CA3 is proposed as a possible location for this "multichart" architecture; however, other implementations in anatomy would not invalidate the main concepts. The model is implemented numerically both as a network of integrate-and-fire units and as a "macroscopic" (with respect to the space of states) description of the system, based on a continuous approximation defined by a system of stochastic differential equations. It provides an explanation for a number of hitherto perplexing observations on hippocampal place fields, including doubling, vanishing, reshaping in distorted environments, acquiring directionality in a two-goal shuttling task, rapid formation in a novel environment, and slow rotation after disorientation. The model makes several new predictions about the expected properties of hippocampal place cells and other cells of the proposed network. It is known from individual and multiple parallel recordings of single-neuron activity in freely moving rodents that the dynamics of the rodent hippocampus during active locomotion in a planar maze is essentially two-dimensional in its space of states; furthermore, it is a two-dimensional model of the animal's motion on the maze (O' Keefe and Dostrovsky, 1971;O'Keefe and Nadel, 1978;Wilson and McNaughton, 1993). This statement becomes clear when one considers a chart, i.e., an abstract plane, on which all place cells are symbolically represented by units (nodes). The fact is that there exists an arrangement of units on a chart such that a typical distribution of neuronal activity over a chart (Fig. 1) is a localized activit y pack et of an invariant shape, the center of which, given a certain fixed mapping from the chart onto the environment, points to the current location of the rat's head.As experimental data show, the activity packet has the following dynamical properties. (1) It persists and retains its shape during active locomotion ...

Hippocampal‐neocortical interactions in memory have typically been characterized within the “standard model” of memory consolidation. In this view, memory storage initially requires hippocampal linking of dispersed neocortical storage sites, but over time this need dissipates, and the hippocampal component is rendered unnecessary. This change in function over time is held to account for the retorgrade amnesia (RA) gradients often seen in patients with hippocampal damage. Recent evidence, however, calls this standard model into question, and we have recently proposed a new approach, the “multiple memory trace” (MMT) theory. In this view, hippocampal ensembles are always involved in storage and retrieval of episodic information, but semantic (gist) information can be established in neocortex, and will survive damage to the hippocampal system if enough time has elapsed. This approach accounts more readily for the very long RA gradients often observed in amnesia. We report the results of analytic and connectionist simulations that demonstrate the feasibility of MMT. We also report a neuroimaging study showing that retrieval of very remote (25‐year‐old) memories elicits as much activation in hippocampus as retrieval of quite recent memories. Finally, we report new data from the study of patients with temporal lobe damage, using more sensitive measures than previously the case, showing that deficits in both episodic and spatial detail can bed observed even for very remote memories. Overall, these findings indicate that the standard model of memory consolidation, which views the hippocampus as having only a temporary role in memory, is wrong. Instead, the data support the view that for episodic and spatial detail the hippocampal system is always necessary. Hippocampus 10:352–368, 2000 © 2000 Wiley‐Liss, Inc.

■ We present the broad outlines of a roadmap toward human-level artificial general intelligence (henceforth, AGI). We begin by discussing AGI in general, adopting a pragmatic goal for its attainment and a necessary foundation of characteristics and requirements. An initial capability landscape will be presented, drawing on major themes from developmental psychology and illuminated by mathematical, physiological, and information-processing perspectives. The challenge of identifying appropriate tasks and environments for measuring AGI will be addressed, and seven scenarios will be presented as milestones suggesting a roadmap across the AGI landscape along with directions for future research and collaboration.This article is the result of an ongoing collaborative effort by the coauthors, preceding and during the AGI Roadmap Workshop held at the University of Of course, this is far from the first attempt to plot a course toward humanlevel AGI: arguably this was the goal of the founders of the field of artificial intelligence in the 1950s, and has been pursued by a steady stream of AI researchers since, even as the majority of the AI field has focused its attention on more narrow, specific subgoals. The ideas presented here build on the ideas of others in innumerable ways, but to review the history of AI

Hippocampal-neocortical interactions in memory have typically been characterized within the "standard model" of memory consolidation. In this view, memory storage initially requires hippocampal linking of dispersed neocortical storage sites, but over time this need dissipates, and the hippocampal component is rendered unnecessary. This change in function over time is held to account for the retrograde amnesia (RA) gradients often seen in patients with hippocampal damage. Recent evidence, however, calls this standard model into question, and we have recently proposed a new approach, the "multiple memory trace" (MMT) theory. In this view, hippocampal ensembles are always involved in storage and retrieval of episodic information, but semantic (gist) information can be established in neocortex, and will survive damage to the hippocampal system if enough time has elapsed. This approach accounts more readily for the very long RA gradients often observed in amnesia. We report the results of analytic and connectionist simulations that demonstrate the feasibility of MMT. We also report a neuroimaging study showing that retrieval of very remote (25-year-old) memories elicits as much activation in hippocampus as retrieval of quite recent memories. Finally, we report new data from the study of patients with temporal lobe damage, using more sensitive measures than previously the case, showing that deficits in both episodic and spatial detail can be observed even for very remote memories. Overall, these findings indicate that the standard model of memory consolidation, which views the hippocampus as having only a temporary role in memory, is wrong. Instead, the data support the view that for episodic and spatial detail the hippocampal system is always necessary.

The goal of this work is to extend the theoretical understanding of the relationship between hippocampal spatial and memory functions to the level of neurophysiological mechanisms underlying spatial navigation and episodic memory retrieval. The proposed unifying theory describes both phenomena within a unique framework, as based on one and the same pathfinding function of the hippocampus. We propose a mechanism of reconstruction of the context of experience involving a search for a nearly shortest path in the space of remembered contexts. To analyze this concept in detail, we define a simple connectionist model consistent with available rodent and human neurophysiological data. Numerical study of the model begins with the spatial domain as a simple analogy for more complex phenomena. It is demonstrated how a nearly shortest path is quickly found in a familiar environment. We prove numerically that associative learning during sharp waves can account for the necessary properties of hippocampal place cells. Computational study of the model is extended to other cognitive paradigms, with the main focus on episodic memory retrieval. We show that the ability to find a correct path may be vital for successful retrieval. The model robustly exhibits the pathfinding capacity within a wide range of several factors, including its memory load (up to 30,000 abstract contexts), the number of episodes that become associated with potential target contexts, and the level of dynamical noise. We offer several testable critical predictions in both spatial and memory domains to validate the theory. Our results suggest that (1) the pathfinding function of the hippocampus, in addition to its associative and memory indexing functions, may be vital for retrieval of certain episodic memories, and (2) the hippocampal spatial navigation function could be a precursor of its memory function.The phenomenon of hippocampal spatial representations and the hippocampal role in episodic memory retrieval remain two of the most puzzling mysteries in cognitive neuroscience that intuitively seem to be connected to each other. Since the finding that the hippocampus plays a pivotal role in long-term memory consolidation (Scoville and Milner 1957; Zola-Morgan and Squire 1986), many proposals have been made regarding its specific role (Teyler and Discenna 1985;Squire 1987;O'Reilly and McClelland 1994;McClelland et al. 1995). A prominent view of the mechanisms underlying consolidation of episodic memories involves fast formation (e.g., via Hebbian mechanisms) of strong associations between hippocampal sparse patterns of activity and distributed neocortical representations. As a result, the former subsequently serve as pointers to the latter. This memory-indexing theory that goes back to Teyler andDiscenna (1985, 1986) and underlies several subsequent major theoretical contributions to the field (Nadel and Wheeler et al. 1997;Tulving 2002) assumes that a memory of an episode is retrieved by reactivating a hippocampal pointer to it. Consistent with this view, r...