Editor's Review and Introduction: Cognition-Inspired Artificial Intelligence.

Cognitive science has much to contribute to the general scientific body of knowledge, but it is also a field rife with possibilities for providing background research that can be leveraged by artificial intelligence (AI) developers. In this introduction, we briefly explore the history of AI. We particularly focus on the relationship between AI and cognitive science and introduce this special issue that promotes the method of inspiring AI development with the results of cognitive science research.

Symbolic Deep Networks: A Psychologically Inspired Lightweight and Efficient Approach to Deep Learning.

The last two decades have produced unprecedented successes in the fields of artificial intelligence and machine learning (ML), due almost entirely to advances in deep neural networks (DNNs). Deep hierarchical memory networks are not a novel concept in cognitive science and can be traced back more than a half century to Simon's early work on discrimination nets for simulating human expertise. The major difference between DNNs and the deep memory nets meant for explaining human cognition is that the latter are symbolic networks meant to model the dynamics of human memory and learning. Cognition-inspired symbolic deep networks (SDNs) address several known issues with DNNs, including (1) learning efficiency, where a much larger number of training examples are required for DNNs than would be expected for a human; (2) catastrophic interference, where what is learned by a DNN gets unlearned when a new problem is presented; and (3) explainability, where there is no way to explain what is learned by a DNN. This paper explores whether SDNs can achieve similar classification accuracy performance to DNNs across several popular ML datasets and discusses the strengths and weaknesses of each approach. Simulations reveal that (1) SDNs provide similar accuracy to DNNs in most cases, (2) SDNs are far more efficient than DNNs, (3) SDNs are as robust as DNNs to irrelevant/noisy attributes in the data, and (4) SDNs are far more robust to catastrophic interference than DNNs. We conclude that SDNs offer a promising path toward human-level accuracy and efficiency in category learning. More generally, ML frameworks could stand to benefit from cognitively inspired approaches, borrowing more features and functionality from models meant to simulate and explain human learning.

Cognitive Models in Cybersecurity: Learning From Expert Analysts and Predicting Attacker Behavior.

Cybersecurity stands to benefit greatly from models able to generate predictions of attacker and defender behavior. On the defender side, there is promising research suggesting that Symbolic Deep Learning (SDL) may be employed to automatically construct cognitive models of expert behavior based on small samples of expert decisions. Such models could then be employed to provide decision support for non-expert users in the form of explainable expert-based suggestions. On the attacker side, there is promising research suggesting that model-tracing with dynamic parameter fitting may be used to automatically construct models during live attack scenarios, and to predict individual attacker preferences. Predicted attacker preferences could then be exploited for mitigating risk of successful attacks. In this paper we examine how these two cognitive modeling approaches may be useful for cybersecurity professionals via two human experiments. In the first experiment participants play the role of cyber analysts performing a task based on Intrusion Detection System alert elevation. Experiment results and analysis reveal that SDL can help to reduce missed threats by 25%. In the second experiment participants play the role of attackers picking among four attack strategies. Experiment results and analysis reveal that model-tracing with dynamic parameter fitting can be used to predict (and exploit) most attackers' preferences 40-70% of the time. We conclude that studies and models of human cognition are highly valuable for advancing cybersecurity.

Simulations in Cyber-Security: A Review of Cognitive Modeling of Network Attackers, Defenders, and Users.

Computational models of cognitive processes may be employed in cyber-security tools, experiments, and simulations to address human agency and effective decision-making in keeping computational networks secure. Cognitive modeling can addresses multi-disciplinary cyber-security challenges requiring cross-cutting approaches over the human and computational sciences such as the following: (a) adversarial reasoning and behavioral game theory to predict attacker subjective utilities and decision likelihood distributions, (b) human factors of cyber tools to address human system integration challenges, estimation of defender cognitive states, and opportunities for automation, (c) dynamic simulations involving attacker, defender, and user models to enhance studies of cyber epidemiology and cyber hygiene, and (d) training effectiveness research and training scenarios to address human cyber-security performance, maturation of cyber-security skill sets, and effective decision-making. Models may be initially constructed at the group-level based on mean tendencies of each subject's subgroup, based on known statistics such as specific skill proficiencies, demographic characteristics, and cultural factors. For more precise and accurate predictions, cognitive models may be fine-tuned to each individual attacker, defender, or user profile, and updated over time (based on recorded behavior) via techniques such as model tracing and dynamic parameter fitting.

Model flexibility analysis.

A good fit of model predictions to empirical data are often used as an argument for model validity. However, if the model is flexible enough to fit a large proportion of potential empirical outcomes, finding a good fit becomes less meaningful. We propose a method for estimating the proportion of potential empirical outcomes that the model can fit: Model Flexibility Analysis (MFA). MFA aids model evaluation by providing a metric for gauging the persuasiveness of a given fit. We demonstrate that MFA can be more informative than merely discounting the fit by the number of free parameters in the model, and show how the number of free parameters does not necessarily correlate with the flexibility of the model. Additionally, we contrast MFA with other flexibility assessment techniques, including Parameter Space Partitioning, Model Mimicry, Minimum Description Length, and Prior Predictive Evaluation. Finally, we provide examples of how MFA can help to inform modeling results and discuss a variety of issues relating to the use of MFA in model validation. (PsycINFO Database Record

SAwSu: an integrated model of associative and reinforcement learning.

Successfully explaining and replicating the complexity and generality of human and animal learning will require the integration of a variety of learning mechanisms. Here, we introduce a computational model which integrates associative learning (AL) and reinforcement learning (RL). We contrast the integrated model with standalone AL and RL models in three simulation studies. First, a synthetic grid-navigation task is employed to highlight performance advantages for the integrated model in an environment where the reward structure is both diverse and dynamic. The second and third simulations contrast the performances of the three models in behavioral experiments, demonstrating advantages for the integrated model in accounting for behavioral data.

Goal-proximity decision-making.

Reinforcement learning (RL) models of decision-making cannot account for human decisions in the absence of prior reward or punishment. We propose a mechanism for choosing among available options based on goal-option association strengths, where association strengths between objects represent previously experienced object proximity. The proposed mechanism, Goal-Proximity Decision-making (GPD), is implemented within the ACT-R cognitive framework. GPD is found to be more efficient than RL in three maze-navigation simulations. GPD advantages over RL seem to grow as task difficulty is increased. An experiment is presented where participants are asked to make choices in the absence of prior reward. GPD captures human performance in this experiment better than RL.

TreePlus: interactive exploration of networks with enhanced tree layouts.

Despite extensive research, it is still difficult to produce effective interactive layouts for large graphs. Dense layout and occlusion make food webs, ontologies, and social networks difficult to understand and interact with. We propose a new interactive Visual Analytics component called TreePlus that is based on a tree-style layout. TreePlus reveals the missing graph structure with visualization and interaction while maintaining good readability. To support exploration of the local structure of the graph and gathering of information from the extensive reading of labels, we use a guiding metaphor of "Plant a seed and watch it grow." It allows users to start with a node and expand the graph as needed, which complements the classic overview techniques that can be effective at (but often limited to) revealing clusters. We describe our design goals, describe the interface, and report on a controlled user study with 28 participants comparing TreePlus with a traditional graph interface for six tasks. In general, the advantage of TreePlus over the traditional interface increased as the density of the displayed data increased. Participants also reported higher levels of confidence in their answers with TreePlus and most of them preferred TreePlus.