Exploring the Computational Explanatory Gap

Reggia, James A.; Huang, Di-Wei; Katz, Garrett E.

doi:10.3390/philosophies2010005

Cited by 16 publications

(26 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…present-day robots and simulated life forms, e.g. Reggia, 2013;Reggia, Monner, & Sylvester, 2014). In essence, robots and computer simulations demonstrate how pain-like behaviour can be produced without the subjective experience of pain.…”

Section: Are Insects More Like Little People or Complicated Robots?mentioning

confidence: 99%

Do insects feel pain? A question at the intersection of animal behaviour, philosophy and robotics

Adamo

2016

Animal Behaviour

View full text Add to dashboard Cite

Section: Are Insects More Like Little People or Complicated Robots?mentioning

confidence: 99%

Do insects feel pain? A question at the intersection of animal behaviour, philosophy and robotics

Adamo

2016

Animal Behaviour

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 96%

“…Top-down symbolic methods are largely just the opposite. This complementarity has been recognized in the past (Reggia et al, 2014) and leveraged effectively in a number of cognitive architectures (e.g., Sun and Naveh, 2004).The current limited abilities of neural architectures to capture critical aspects of high-level cognition puts them at a tremendous disadvantage relative to symbolic AI techniques when trying to engineer neurocomputational systems for high-level problem-solving tasks. Such problem solving by people depends on cognitive control, the process of managing other cognitive processes (Schneider and Chein, 2003).…”

mentioning

confidence: 99%

“…Developing purely neurocomputational systems for high-level problem solving could ultimately provide several significant practical advantages. For example, when compared to traditional top-down AI, neural computation is fault tolerant, and it has the potential for great speed due to its inherent parallel processing (Haykin, 2009;Reggia et al, 2014). The latter is particularly true given the recent increasing availability of parallel computing hardware such as neural network chips and GPU clusters.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Engineering neural systems for high-level problem solving

Sylvester

Reggia

2016

Neural Networks

Self Cite

View full text Add to dashboard Cite

There is a long-standing, sometimes contentious debate in AI concerning the relative merits of a symbolic, top-down approach vs. a neural, bottom-up approach to engineering intelligent machine behaviors. While neurocomputational methods excel at lower-level cognitive tasks (incremental learning for pattern classification, low-level sensorimotor control, fault tolerance and processing of noisy data, etc.), they are largely non-competitive with top-down symbolic methods for tasks involving high-level cognitive problem solving (goal-directed reasoning, metacognition, planning, etc.). Here we take a step towards addressing this limitation by developing a purely neural framework named galis. Our goal in this work is to integrate top-down (non-symbolic) control of a neural network system with more traditional bottom-up neural computations. galis is based on attractor networks that can be "programmed" with temporal sequences of hand-crafted instructions that control problem solving by gating the activity retention of, communication between, and learning done by other neural networks. We demonstrate the effectiveness of this approach by showing that it can be applied successfully to solve sequential card matching problems, using both human performance and a top-down symbolic algorithm as experimental controls. Solving this kind of problem makes use of top-down attention control and the binding together of visual features in ways that are easy for symbolic AI systems but not for neural networks to achieve. Our model can not only be instructed on how to solve card matching problems successfully, but its performance also qualitatively (and sometimes quantitatively) matches the performance of both human subjects that we had perform the same task and the top-down symbolic algorithm that we used as an experimental control. We conclude that the core principles underlying the galis framework provide a promising approach to engineering purely neurocomputational systems for problem-solving tasks that in people require higher-level cognitive functions.

show abstract

“…stimuli. Previous studies have noted that the gap between traditional artificial neural 653 network architectures and symbolic systems is one of the great challenges to be 654 overcome by artificial intelligence [86]. Previous neural network models that attempt to 655 implement a similar approach to memory control have relied on predetermined, 656 hand-coded sequences of memory operations hard-coded into the model ( [87][88][89], but 657 see [50]).…”

mentioning

confidence: 99%

Flexible working memory through selective gating and attentional tagging

Kruijne

Bohté

Roelfsema

et al. 2019

Preprint

View full text Add to dashboard Cite

Working memory is essential for intelligent behavior as it serves to guide behavior of humans and nonhuman primates when task-relevant stimuli are no longer present to the senses. Moreover, complex tasks often require that multiple working memory representations can be flexibly and independently maintained, prioritized, and updated according to changing task demands. Thus far, neural network models of working memory have been unable to offer an integrative account of how such control mechanisms are implemented in the brain and how they can be acquired in a biologically plausible manner. Here, we present WorkMATe, a neural network architecture that models cognitive control over working memory content and learns the appropriate control operations needed to solve complex working memory tasks. Key components of the model include a gated memory circuit that is controlled by internal actions, encoding sensory information through untrained connections, and a neural circuit that matches sensory inputs to memory content. The network is trained by means of a biologically plausible reinforcement learning rule that relies on attentional feedback and reward prediction errors to guide synaptic updates. We demonstrate that the model successfully acquires policies to solve classical working memory tasks, such as delayed match-to-sample and delayed pro-saccade/antisaccade tasks. In addition, the model solves much more complex tasks including the hierarchical 12-AX task or the ABAB ordered recognition task, which both demand an agent to independently store and updated multiple items separately in memory. Furthermore, the control strategies that the model acquires for these tasks subsequently generalize to new task contexts with novel stimuli. As such, WorkMATe provides a new solution for the neural implementation of flexible memory control. Author SummaryWorking Memory, the ability to briefly store sensory information and use it to guide behavior, is a cornerstone of intelligent behavior. Existing neural network models of Working Memory typically focus on how information is stored and maintained in the brain, but do not address how memory content is controlled: how the brain can November 13, 2019 1/30 selectively store only stimuli that are relevant for a task, or how different stimuli can be maintained in parallel, and subsequently replaced or updated independently according to task demands. The models that do implement control mechanisms are typically not trained in a biologically plausible manner, and do not explain how the brain learns such control. Here, we present WorkMATe, a neural network architecture that implements flexible cognitive control and learns to apply these control mechanisms using a biologically plausible reinforcement learning method. We demonstrate that the model acquires control policies to solve a range of both simple and more complex tasks. Moreover, the acquired control policies generalize to new situations, as with human cognition. This way, WorkMATe provides new insights into the neural organization of...

show abstract

Exploring the Computational Explanatory Gap

Cited by 16 publications

References 67 publications

Do insects feel pain? A question at the intersection of animal behaviour, philosophy and robotics

Do insects feel pain? A question at the intersection of animal behaviour, philosophy and robotics

Engineering neural systems for high-level problem solving

Flexible working memory through selective gating and attentional tagging

Contact Info

Product

Resources

About