# Cognitive Architecture **Domain:** Cognitive Science / Artificial Intelligence / Systems Theory **Doc Type:** Technical Concept Node **Maturity:** Developing **Related:** [[wiki/Computational Architecture|Computational Architecture]], [[wiki/Recursive Self-Model|Recursive Self-Model]], [[wiki/Joscha Bach|Joscha Bach]] --- ## Definition A **cognitive architecture** is an explicit organization of the processes and representations proposed to support perception, memory, learning, motivation, action selection, reasoning, and self-modeling within an intelligent system. ## Ontology Context This node owns system-level theories of how cognitive functions fit together. [[wiki/Computational Architecture|Computational Architecture]] owns the more general arrangement of computational components; [[wiki/Recursive Self-Model|Recursive Self-Model]] owns the specific capacity of a system to represent and update a model of itself. ## See Also [[wiki/Computational Architecture|Computational Architecture]] · [[wiki/Recursive Self-Model|Recursive Self-Model]] · [[wiki/Mechanistic Intelligence|Mechanistic Intelligence]] · [[wiki/Joscha Bach|Joscha Bach]] · [[wiki/Society of Mind|Society of Mind]] ## Simple Reminders, Quotations, and Thoughts > "AI people try to build models of the parts we do understand." > **— Roger Schank**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Machine Succession/AI Models Only the Parts of Thought We Understand by Roger Schank|AI Models Only the Parts of Thought We Understand by Roger Schank]] > "Computation is still the best, indeed the only, scientific explanation we have of how a physical object like a brain can act intelligently." > **— Alison Gopnik**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Information/Computation Is Our Best Explanation of Intelligent Brains by Alison Gopnik|Computation Is Our Best Explanation of Intelligent Brains by Alison Gopnik]] > "It is not that thinking machines will be emulating human minds any time soon: quite the reverse. We are cleaning up our acts, embarrassed by the fumbling inconclusiveness of messy thinking." > **— Ziyad Marar**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Machine Succession/Humans May Be Learning to Think Like Machines by Ziyad Marar|Humans May Be Learning to Think Like Machines by Ziyad Marar]] > "Machines can faithfully imitate the results of some human thought processes whose outcomes are fixed (remembering people's favorite movies, recognizing familiar objects) or dynamic (jet piloting, grand master chess play)." > **— Scott Atran**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Memory/Machines Can Imitate Fixed and Dynamic Human Thought by Scott Atran|Machines Can Imitate Fixed and Dynamic Human Thought by Scott Atran]] > "Conscious machines. Intelligent machines are inevitable — by some measures they are already here. Synthetic consciousness would be a much greater breakthrough, in some ways a more profound one than finding life on other planets. One problem: We don't understand how consciousness works, so recreating it will require learning a lot more about what it means to be both smart and self-aware. Another problem: We don't understand what consciousness is, so it's not clear what "smart" and "self-aware" mean, exactly. Gerald Edelman's brain-based devices are a promising solution. Rather than trying to deconstruct the brain as a computer, they construct neural processing from the bottom up, mimicking the workings of actual neurons. Odds: 50-50." > **— Corey S. Powell**, *2009, Edge Annual Question, “What Will Change Everything?”* [[reminders/Consciousness/Synthetic Consciousness Could Surpass Finding Alien Life by Corey S. Powell|Synthetic Consciousness Could Surpass Finding Alien Life by Corey S. Powell]] > "There is also exceptionally high potential for applications of transfer learning. So much of the practical value of machine learning, for example in search and information retrieval, has traditionally focused on systems that learn from the massive datasets and people available on the World-Wide Web. But what can web-trained systems learn about smaller communities, organizations, or even individuals? Can we foresee a future where intelligent machines are able to learn useful tasks that are highly specialized to a specific individual or small organization? Transfer learning opens the possibility that all the intelligence of the web can form the foundation of machine-learned systems, from which more individualized intelligence is learned, through transfer learning. Achieving this would amount to another step towards the democratization of machine intelligence." > **— Peter Lee**, *2017, Edge Annual Question, “What Scientific Term or Concept Ought to Be More Widely Known?”* [[reminders/AI Control/Transfer Learning Could Democratize Personalized Machine Intelligence by Peter Lee|Transfer Learning Could Democratize Personalized Machine Intelligence by Peter Lee]] > "Hidden layers embody, in a concrete physical form, the fashionable but rather vague and abstract idea of emergence. Each hidden layer neuron has a template. It becomes activated, and sends signals of its own to the next layer, precisely when the pattern of information it's receiving from the preceding layer matches (within some tolerance) that template. But this is just to say, in precision-enabling jargon, that the neuron defines, and thus creates, a new emergent concept." > **— Frank Wilczek**, *2011, Edge Annual Question, “What Scientific Concept Would Improve Everybody's Cognitive Toolkit?”* [[reminders/Information/Hidden Layers Create New Emergent Concepts by Frank Wilczek|Hidden Layers Create New Emergent Concepts by Frank Wilczek]] > “How does a single human brain architecture create many kinds of human minds?” > **— Lisa Feldman Barrett**, *2018 Edge Annual Question, question* [[reminders/Consciousness/How Can One Brain Architecture Make Many Kinds of Minds by Lisa Feldman Barrett|How Can One Brain Architecture Make Many Kinds of Minds by Lisa Feldman Barrett]] > “Are we smart enough to know when we’ve reached the limits of our ability to understand the universe?” > **— David Pizarro**, *2018 Edge Annual Question, question* [[reminders/Consciousness/Can We Recognize the Limits of Human Understanding by David Pizarro|Can We Recognize the Limits of Human Understanding by David Pizarro]] > “Is our brain fundamentally limited in its ability to understand the external world?” > **— Stanislas Dehaene**, *2018 Edge Annual Question, question* [[reminders/Consciousness/Is the Brain Fundamentally Limited in What It Can Understand by Stanislas Dehaene|Is the Brain Fundamentally Limited in What It Can Understand by Stanislas Dehaene]] > “How can the few pounds of grey goo between our ears let us make utterly surprising, completely unprecedented, and remarkably true discoveries about the world around us, in every domain and at every scale, from quarks to quasars?” > **— Alison Gopnik**, *2018 Edge Annual Question, question* [[reminders/Consciousness/How Can Grey Matter Discover Truths From Quarks to Quasars by Alison Gopnik|How Can Grey Matter Discover Truths From Quarks to Quasars by Alison Gopnik]] > “Our brains may end up as a collection of highly specialised 'modules', but the functioning of these modules is not the key to intelligence. The key is the deeper set of rules that enable a homogeneous pink goo to wire itself up into such a collection of specialised machines in the first place, merely by being exposed to the sensory world.” > **— Steve Grand**, *2004 Edge Annual Question, response passage* [[reminders/Consciousness/Intelligence Depends on the Rules That Wire the Brain by Steve Grand|Intelligence Depends on the Rules That Wire the Brain by Steve Grand]] > “First, the idea that each of us relies primarily on one or the other hemisphere is not empirically justifiable. The evidence indicates that each of us uses all of our brain, not primarily one side or the other. The brain is a single, interactive system, with the parts working in concert to accomplish a given task.” > **— Stephen M. Kosslyn**, *2014 Edge Annual Question, response passage* [[reminders/Consciousness/The Brain Is One Interactive System Not Two Rival Sides by Stephen M. Kosslyn|The Brain Is One Interactive System Not Two Rival Sides by Stephen M. Kosslyn]] > “Human intelligence is a product of analogy and combinatorics. Analogy allows the mind to use a few innate ideas—space, force, essence, goal—to understand more abstract domains.” > **— Steven Pinker**, *2004 Edge Annual Question, response passage* [[reminders/Human Animality/Analogy and Combinatorics Build Human Intelligence by Steven Pinker|Analogy and Combinatorics Build Human Intelligence by Steven Pinker]] > “The mind consists of genetically-determined hardware and experientially-determined software. The hardware components are not constructed by genes working either individually or additively but, rather, by groups of genes working sequentially and configurally.” > **— David Lykken**, *2004 Edge Annual Question, response passage* [[reminders/Evolution/Genes and Experience Shape the Mind by David Lykken|Genes and Experience Shape the Mind by David Lykken]] > “There are no clear-cut level distinctions in nature. Neural software bleeds into neural firmware, neural firmware bleeds into neural hardware, psychology bleeds into biology and biology bleeds into physics. Body bleeds into mind and mind bleeds into world.” > **— Andy Clark**, *2004 Edge Annual Question, response passage* [[reminders/Information/Mind Body and Biology Have No Clear Boundaries by Andy Clark|Mind Body and Biology Have No Clear Boundaries by Andy Clark]] > “The brain is what the brain creates. Its workings reflect the workings of everything it creates.” > **— Todd Siler**, *2004 Edge Annual Question, response passage* [[reminders/Information/The Brain Reflects What It Creates by Todd Siler|The Brain Reflects What It Creates by Todd Siler]] ## Relationships - **Edge Annual Question source relationship:** [[collections/Edge|Edge]] preserves the annual-question source corpus from which a proposition-specific quotation is connected to this entry.