IDA and LIDA
Projects: IDA and LIDA
PI: Stan Franklin
Wouldn't our jobs be easier if computers could do more of our tedious, but exacting
tasks for us? In an important way, the United States Navy believes so.
With an Intelligent Distribution Agent (IDA), the Navy has an intelligent software representative that automates the decision-making process for assigning sailors to their new posts. By communicating with sailors by email, much as a human would, IDA can negotiate new jobs and eventually make assignments based on Navy policies and the sailors' preferences. Basically, IDA technology:
accesses the Navy's many large databases (personnel job requisition, training classes,
etc.)
applies tremendous processing power to sort through all of the facts to consider in
the databases, and
applies other human-like brain mechanisms to make the best decision for the individual
sailor and the Navy.
IDA shows promise for fully automating the jobs of information providers and decision-makers
such as customer service agents, travel agents, and loan officers.
A significant extension of IDA, the LIDA (Learning IDA) project adds several types of learning. LIDA is a broad, comprehensive cognitive architecture that attempts to model how minds work. As such LIDA will provide hypotheses and direction for future research.
Past Funding:
- Multiple grants for IDA project. PI(UM): Stan Franklin. Funding Agency: Office of
Naval Research. $1,500,000.
Selected Publications:
- Franklin, S., Madl, T., Strain, S., Faghihi, U., Dong, D., Kugele, S., Snaider, J., Agrawal, P., Chen, S. (2016). A LIDA cognitive model tutorial. Biologically Inspired Cognitive Architectures, 105-130. doi: 10.1016/j.bica.2016.04.003
- Dong, D., & Franklin, S. (2015). A New Action Execution Module for the Learning Intelligent Distribution Agent (LIDA): The Sensory Motor System. Cognitive Computation. doi: 10.1007/s12559-015-9322-3.
- Franklin, S., Madl, T., D'Mello, S., & Snaider, J. (2014). LIDA: A Systems-level Architecture
for Cognition, Emotion, and Learning. IEEE Transactions on Autonomous Mental Development,
6(1), 19-41.
doi: 10.1109/TAMD.2013.2277589 - Franklin, S., Strain, S., McCall, R., & Baars, B. (2013). Conceptual Commitments of the LIDA Model of Cognition. Journal of Artificial General Intelligence, 4(2), 1-24, DOI: 10.2478/jagi-2013-0002
- Faghihi, U., & Franklin, S. (2012). The LIDA Model as a Foundational Architecture for AGI. In P. Wang & B. Goertzel (Eds.), Theoretical Foundations of Artificial General Intelligence (pp. 105-123). Paris: Atlantis Press.
- Franklin, S., Strain, S., Snaider, J., McCall, R., & Faghihi, U. (2012). Global Workspace Theory, its LIDA Model and the Underlying Neuroscience. Biologically Inspired Cognitive Architectures, 1, 32-43. doi: 10.1016/j.bica.2012.04.001
- McCauley, L., and S. Franklin . 2002. A Large-Scale Multi-Agent System for Navy Personnel Distribution. Connection Science, 14, 371-385.
LIDA Model: Computational Framework
PI: Stan Franklin
Intelligent software agents aiming toward general intelligence are complex systems
and, as such, are difficult and time consuming to implement and to customize. A software
framework is a reusable implementation of the skeleton of a software system, capturing
its generic functionality. By significantly reducing the amount of effort necessary
to develop customized applications, frameworks are becoming increasingly attractive
for the implementation of intelligent software agents.
The LIDA Framework is a generic and customizable computational implementation of the LIDA model, programmed in Java. It allows for the relatively rapid development of LIDA controlled software agents for specific problem domains, using a declarative specification of the agent architecture by an XML file. Small pieces of the system, and even the internal implementation of whole modules, can be customized. Since biological minds operate in parallel, the Framework provides for multithreading support. Its implementation adheres to several well-established design principles, and best programming practices. The LIDA Framework is available online for research use, and has been used to produce, so far, four LIDA based software agents, resulting in two publications.
Selected Publications
- Faghihi, U., McCall, R., & Franklin, S. (2012). A Computational Model of Attentional Learning in a Cognitive Agent. Biologically Inspired Cognitive Architectures, 2, 25-36.
- Madl, T., & Franklin, S. (2012). A LIDA-based Model of the Attentional Blink. Proceedings of the 11th International Conference on Cognitive Modeling (ICCM 2012).
- Madl, T., Baars, B. J., & Franklin, S. (2011). The Timing of the Cognitive Cycle. PLoS ONE, 6(4), e14803.
- Snaider, J., McCall, R., & Franklin, S. (2011). The LIDA Framework as a General Tool for AGI. The Fourth Conference on Artificial General Intelligence.
LIDA Model: Experiment Replication
PI: Stan Franklin
Touted as a cognitive model, LIDA must constitute a valid scientific model of how
minds work. A major way to test this is through the replication of data from existing
psychological experiments. This project involves building software agents based on
the LIDA model to perform experiments, and comparing the results to those from human
or animal subjects. Compatible results constitute evidence for the LIDA model. Incompatible
results necessitate some updating of the model or its parameters. We've learned something.
Science is working. In addition to testing the LIDA model, such work thus contributes
to the identification of the internal parameters for the model including determining
appropriate values. Until now, we've replicated two such experiments bearing on the
timing of the action-perception cycle, one modeling the attentional blink phenomenon,
and another exploring executive attention. The first three are published.
Selected Publications:
- Dong, D., Franklin, S., & Agrawal, P. (2015). Estimating Human Movements Using Memory of Errors. Procedia Computer Science, 71, 1-10. doi: 10.1016
LIDA Model: Medical Agent X (MAX)
PI: Stan Franklin
A real world application of the LIDA model, Medical Agent X (MAX) will be a LIDA-based
software agent situated in hybrid real and digital environment composed of healthcare
providers, clinical data regarding the providers' patients, and the diagnostic possibilities
associated with that data. MAX will use human-style reasoning, and will communicate
with the providers in natural language. It will generate diagnostic hypotheses by
analyzing clinical data, and utilize clinical knowledge to investigate those hypotheses.
Furthermore, MAX will be able to learn by communicating with humans, by consulting
medical literature, and from its own experience.
Selected Publications:
- Strain, S., Kugele, S., & Franklin, S. (2014). The Learning Intelligent Distribution Agent (LIDA) and Medical Agent X (MAX): Computational Intelligence for Medical Diagnosis. Proceedings of the IEEE Symposium Series on Computational Intelligence, Orlando, FL (SSCI 2014), Symposium on Computational Intelligence for Human-like Intelligence (CIHLI), 78-85.
- Strain, S., & Franklin, S. (2011). Modeling medical diagnosis using a comprehensive cognitive architecture. Journal of Healthcare Engineering, 2(2), 241-257.
LIDA Model: From Perception to Cognition
PI: Stan Franklin
Intelligent agents operating in complex "real-world" environments must generate their
own understanding of their current situation from their sensory primitives. In some
cases, for example in the visual modality in humans, the process of meaning creation
and understanding is exceedingly complex. Cognitive architectures have historically
eschewed considerations of the details of perception, and of reconciling high-level
representations, useful for reasoning, logic, and planning, with high-dimensional,
transient, noisy sensory stimuli. In this project we take a biologically-inspired
view, within a broad cognitive model, LIDA, of how the abstract, invariant, and conceptual
aspects of detailed, low-level sensory representation are recognized and associated.
Such work fleshes out the details of LIDA's Sensory Memory, Perceptual Associative
Memory, and conscious learning. Also covered is the critical relation of attentional
and learning processes with this perceptual process.
Selected Publications:
- Dong, D. & Franklin, S. (2014). Sensory Motor System: Modeling the Process of Action Execution. In M. Bello P., Guarini M., McShane M. & Scassellati B. (Eds.) Proceedings of the 36th Annual Conference of the Cognitive Science Society (pp. 2145-2150). Austin TX: Cognitive Science Society.
- Madl, T., Franklin, S., Chen, K., & Trappl, R. (2013). Spatial Working Memory in the LIDA Cognitive Architecture. In R. West & T. Stewart (Eds.), Proceedings of the 12th International Conference on Cognitive Modelling (pp. 384-390). Ottawa, Canada: Carleton University.
- Faghihi, U., McCall, R., & Franklin, S. (2012). A Computational Model of Attentional Learning in a Cognitive Agent. Biologically Inspired Cognitive Architectures, 2, 25-36.
- Madl, T., & Franklin, S. (2012). A LIDA-based Model of the Attentional Blink. Proceedings of the 11th International Conference on Cognitive Modeling (ICCM 2012).
- Madl, T., Baars, B. J., & Franklin, S. (2011). The Timing of the Cognitive Cycle. PLoS ONE, 6(4), e14803.
Vector LIDA using Extended Integer SDM
PI: Stan Franklin
Sparse distributed memory (SDM) is a mathematical model of human long-term memory
based on large binary vectors. It is distributed, auto-associative, content addressable,
and noise robust. Moreover, it exhibits one-shot learning, is resilient to damage,
and its contents degrade gracefully when the memory fills up. Its interesting psychological
characteristics include interference, knowing when it does not know, and the tip of
the tongue effect. SDM's structure is ideal for parallel processing or hardware implementation.
All this makes it an attractive option for modeling memory modules in cognitive architectures
and other AI applications.
Extended SDM uses a novel mechanism to add hetero-associativity to SDM, making it particularly effective for sequence learning. Integer SDM extends the memory to accept integer vectors, while retaining the benefits of the model. Built upon Extended Integer SDM, Modular Composite Representation (MCR,) allows the representation of complex structures using single vectors, making them attractive for modeling internal data representations in cognitive architectures.
These technologies constitute the heart of the new Vector LIDA project that is implementing the LIDA architecture using MCR vectors for data representation. Vector LIDA should produce a more realistic and biologically plausible model, better integration with low-level perceptual processing, better scalability, and easier learning mechanisms.
Selected Publications:
- Snaider, J., & Franklin, S. (2014). Vector LIDA. Procedia Computer Science, 41, 188-203.
- Snaider, J., & Franklin, S. (2014). Modular Composite Representation. Cognitive Computation, 6(3), 510-527. doi: 10.1007/s12559-013-9243-ySnaider, J., Franklin, S., Strain, S., & George, E. O. (2013). Integer sparse distributed memory: Analysis and results. Neural Networks.
- Snaider, J., & Franklin, S. (2012). Extended Sparse Distributed Memory and Sequence Storage. Cognitive Computation, 4(2), 172-180. doi: 10.1007/s12559-012-9125-8