Javier Snaider

LIDA: A Systems-level Architecture for Cognition, Emotion, and Learning

We describe a cognitive architecture learning intelligent distribution agent (LIDA) that affords attention, action selection and human-like learning intended for use in controlling cognitive agents that replicate human experiments as well as performing real-world tasks. LIDA combines sophisticated action selection, motivation via emotions, a centrally important attention mechanism, and multimodal instructionalist and selectionist learning. Empirically grounded in cognitive science and cognitive neuroscience, the LIDA architecture employs a variety of modules and processes, each with its own effective representations and algorithms. LIDA has much to say about motivation, emotion, attention, and autonomous learning in cognitive agents. In this paper, we summarize the LIDA model together with its resulting agent architecture, describe its computational implementation, and discuss results of simulations that replicate known experimental data. We also discuss some of LIDAs conceptual modules, propose nonlinear dynamics as a bridge between LIDAs modules and processes and the underlying neuroscience, and point out some of the differences between LIDA and other cognitive architectures. Finally, we discuss how LIDA addresses some of the open issues in cognitive architecture research.

The LIDA framework as a general tool for AGI

Intelligent software agents aiming for general intelligence are likely to be exceedingly complex systems and, as such, will be difficult to implement and to customize. Frameworks have been applied successfully in large-scale software engineering applications. A framework constitutes the skeleton of the application, capturing its generic functionality. Frameworks are powerful as they promote code reusability and significantly reduce the amount of effort necessary to develop customized applications. They are well suited for the implementation of AGI software agents. Here we describe the LIDA framework, a customizable implementation of the LIDA model of cognition. We argue that its characteristics make it suitable for wider use in developing AGI cognitive architectures.

Extended Sparse Distributed Memory and Sequence Storage

Sparse distributed memory (SDM) is an auto-associative memory system that stores high-dimensional Boolean vectors. SDM uses the same vector for the data (word) and the location where it is stored (address). Here, we present an extension of the original SDM that uses word vectors of larger size than address vectors. This extension preserves many of the desirable properties of the original SDM: auto-associability, content addressability, distributed storage and robustness over noisy inputs. In addition, it adds new functionality, enabling an efficient auto-associative storage of sequences of vectors, as well as of other data structures such as trees. Simulations testing this new memory are described.

Time production and representation in a conceptual and computational cognitive model

Time perception and inferences there from are of critical importance to many autonomous agents. But time is not perceived directly by any sensory organ. We argue that time is constructed by cognitive processes. Here we present a model for time perception that concentrates on succession and duration, and that generates these concepts and others, such as continuity, immediate present duration, and lengths of time. These concepts are grounded through the perceptual process itself. The LIDA cognitive model is used to illustrate these ideas.

Modular Composite Representation

High-dimensional vector spaces have noteworthy properties that make them attractive for representation models. A reduced description model is a mechanism for encoding complex structures as single high-dimensional vectors. Moreover, these vectors can be used to directly process complex operations such as analogies, inferences, and structural comparisons. Also, it is possible to reconstruct the whole structure from the reduced description vector. Here, we introduce the modular composite representation (MCR), a new reduced description model that employs long integer vectors. We also describe several experiments with them, and give a theoretical analysis of the distance distribution in this vector space, and of properties of this representation. Finally, we compare MCR with other two reduced description models: Spatter Code and holographic reduced representation.

Integer sparse distributed memory: Analysis and results

Sparse distributed memory is an auto-associative memory system that stores high dimensional Boolean vectors. Here we present an extension of the original SDM, the Integer SDM that uses modular arithmetic integer vectors rather than binary vectors. This extension preserves many of the desirable properties of the original SDM: auto-associativity, content addressability, distributed storage, and robustness over noisy inputs. In addition, it improves the representation capabilities of the memory and is more robust over normalization. It can also be extended to support forgetting and reliable sequence storage. We performed several simulations that test the noise robustness property and capacity of the memory. Theoretical analyses of the memorys fidelity and capacity are also presented.

Continuity and the Flow of Time: A Cognitive Science Perspective

Modern tools and methods of cognitive science, such as brain imaging or computational modeling, can provide new insights for age-old philosophical questions regarding the nature of temporal experience. This chapter aims to provide an overview of functional consciousness and time perception in brains and minds (Sect. 8.2), and to describe a computational cognitive architecture partially implementing these phenomena (Sects. 8.3, 8.4 and 8.5), and its comparison with data from human behavioral experiments (Sect. 8.6).