We demonstrate that the key components of cognitive architectures (declarative and procedural memory) and their key capabilities (learning, memory retrieval, probability judgment, and utility estimation) can be implemented as algebraic operations on vectors and tensors in a high‐dimensional space using a distributional semantics model. High‐dimensional vector spaces underlie the success of modern machine learning techniques based on deep learning. However, while neural networks have an impressive ability to process data to find patterns, they do not typically model high‐level cognition, and it is often unclear how they work. Symbolic cognitive architectures can capture the complexities of high‐level cognition and provide human‐readable, explainable models, but scale poorly to naturalistic, non‐symbolic, or big data. Vector‐symbolic architectures, where symbols are represented as vectors, bridge the gap between the two approaches. We posit that cognitive architectures, if implemented in a vector‐space model, represent a useful, explanatory model of the internal representations of otherwise opaque neural architectures. Our proposed model, Holographic Declarative Memory (HDM), is a vector‐space model based on distributional semantics. HDM accounts for primacy and recency effects in free recall, the fan effect in recognition, probability judgments, and human performance on an iterated decision task. HDM provides a flexible, scalable alternative to symbolic cognitive architectures at a level of description that bridges symbolic, quantum, and neural models of cognition.
more » « less Award ID(s):
 1734304
 NSFPAR ID:
 10455735
 Publisher / Repository:
 WileyBlackwell
 Date Published:
 Journal Name:
 Cognitive Science
 Volume:
 44
 Issue:
 11
 ISSN:
 03640213
 Format(s):
 Medium: X
 Sponsoring Org:
 National Science Foundation
More Like this

We explore replacing the declarative memory system of the ACTR cognitive architecture with a distributional semantics model. ACTR is a widely used cognitive architecture, but scales poorly to big data applications and lacks a robust model for learning association strengths between stimuli. Distribu tional semantics models can process millions of data points to infer semantic similarities from language data or to in fer product recommendations from patterns of user prefer ences. We demonstrate that a distributional semantics model can account for the primacy and recency effects in free recall, the fan effect in recognition, and human performance on it erated decisions with initially unknown payoffs. The model we propose provides a flexible, scalable alternative to ACT R’s declarative memory at a level of description that bridges symbolic, quantum, and neural models of cognition.more » « less

null (Ed.)Variable binding is a cornerstone of symbolic reasoning and cognition. But how binding can be implemented in connectionist models has puzzled neuroscientists, cognitive psychologists, and neural network researchers for many decades. One type of connectionist model that naturally includes a binding operation is vector symbolic architectures (VSAs). In contrast to other proposals for variable binding, the binding operation in VSAs is dimensionalitypreserving, which enables representing complex hierarchical data structures, such as trees, while avoiding a combinatoric expansion of dimensionality. Classical VSAs encode symbols by dense randomized vectors, in which information is distributed throughout the entire neuron population. By contrast, in the brain, features are encoded more locally, by the activity of single neurons or small groups of neurons, often forming sparse vectors of neural activation. Following Laiho et al. (2015), we explore symbolic reasoning with a special case of sparse distributed representations. Using techniques from compressed sensing, we first show that variable binding in classical VSAs is mathematically equivalent to tensor product binding between sparse feature vectors, another wellknown binding operation which increases dimensionality. This theoretical result motivates us to study two dimensionalitypreserving binding methods that include a reduction of the tensor matrix into a single sparse vector. One binding method for general sparse vectors uses random projections, the other, blocklocal circular convolution, is defined for sparse vectors with block structure, sparse blockcodes. Our experiments reveal that blocklocal circular convolution binding has ideal properties, whereas random projection based binding also works, but is lossy. We demonstrate in example applications that a VSA with blocklocal circular convolution and sparse blockcodes reaches similar performance as classical VSAs. Finally, we discuss our results in the context of neuroscience and neural networks.more » « less

null (Ed.)The ability to encode and manipulate data structures with distributed neural representations could qualitatively enhance the capabilities of traditional neural networks by supporting rulebased symbolic reasoning, a central property of cognition. Here we show how this may be accomplished within the framework of Vector Symbolic Architectures (VSAs) (Plate, 1991; Gayler, 1998; Kanerva, 1996), whereby data structures are encoded by combining highdimensional vectors with operations that together form an algebra on the space of distributed representations. In particular, we propose an efficient solution to a hard combinatorial search problem that arises when decoding elements of a VSA data structure: the factorization of products of multiple codevectors. Our proposed algorithm, called a resonator network, is a new type of recurrent neural network that interleaves VSA multiplication operations and pattern completion. We show in two examples—parsing of a treelike data structure and parsing of a visual scene—how the factorization problem arises and how the resonator network can solve it. More broadly, resonator networks open the possibility of applying VSAs to myriad artificial intelligence problems in realworld domains. The companion article in this issue (Kent, Frady, Sommer, & Olshausen, 2020) presents a rigorous analysis and evaluation of the performance of resonator networks, showing it outperforms alternative approaches.more » « less

We study input compression in a biologically inspired model of neural computation. We demonstrate that a network consisting of a random projection step (implemented via random synaptic connectivity) followed by a sparsification step (implemented via winnertakeall competition) can reduce wellseparated highdimensional input vectors to wellseparated lowdimensional vectors. By augmenting our network with a third module, we can efficiently map each input (along with any small perturbations of the input) to a unique representative neuron, solving a neural clustering problem. Both the size of our network and its processing time, i.e., the time it takes the network to compute the compressed output given a presented input, are independent of the (potentially large) dimension of the input patterns and depend only on the number of distinct inputs that the network must encode and the pairwise relative Hamming distance between these inputs. The first two steps of our construction mirror known biological networks, for example, in the fruit fly olfactory system [Caron et al., 2013; Lin et al., 2014; Dasgupta et al., 2017]. Our analysis helps provide a theoretical understanding of these networks and lay a foundation for how random compression and input memorization may be implemented in biological neural networks. Technically, a contribution in our network design is the implementation of a shortterm memory. Our network can be given a desired memory time t_m as an input parameter and satisfies the following with high probability: any pattern presented several times within a time window of t_m rounds will be mapped to a single representative output neuron. However, a pattern not presented for c⋅t_m rounds for some constant c>1 will be "forgotten", and its representative output neuron will be released, to accommodate newly introduced patterns.more » « less

This article reviews recent progress in the development of the computing framework Vector Symbolic Architectures (also known as Hyperdimensional Computing). This framework is well suited for implementation in stochastic, nanoscale hardware and it naturally expresses the types of cognitive operations required for Artificial Intelligence (AI). We demonstrate in this article that the ringlike algebraic structure of Vector Symbolic Architectures offers simple but powerful operations on highdimensional vectors that can support all data structures and manipulations relevant in modern computing. In addition, we illustrate the distinguishing feature of Vector Symbolic Architectures, “computing in superposition,” which sets it apart from conventional computing. This latter property opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. Vector Symbolic Architectures are Turing complete, as we show, and we see them acting as a framework for computing with distributed representations in myriad AI settings. This paper serves as a reference for computer architects by illustrating techniques and philosophy of VSAs for distributed computing and relevance to emerging computing hardware, such as neuromorphic computing.more » « less