# Artificial Neural Networks **Domain:** Machine Learning / Computational Models **Doc Type:** Concept **Maturity:** Developed **Related:** [[Warren McCulloch]], [[Machine Learning]], [[Reinforcement Learning]], [[Machine Intelligence Continuum]], [[Schedule and Loop]] ## Definition **Artificial neural networks** are computational models composed of connected units whose weighted interactions can be adjusted to learn mappings, representations or policies from data. ## Schedule–Loop Context Early formal neural models helped make internal organization computationally explicit. Modern networks substantially extend those beginnings but preserve the core move from behavior alone toward learned internal structure. ## Backlinks - [[Schedule and Loop]] - [[articles/Schedule and Loop|Schedule and Loop]] ## Simple Reminders, Quotations, and Thoughts > "In principle, a good physics simulator could, very slowly, simulate a brain and its environment." > **— Scott Draves**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Simulation/A Physics Simulator Could Simulate a Brain by Scott Draves|A Physics Simulator Could Simulate a Brain by Scott Draves]] > "Will we increasingly be able to create machines that can produce input-output patterns that replicate human input-output patterns?" > **— Matthew D. Lieberman**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Simulation/Can Machines Replicate Human Behavior From the Outside by Matthew D. Lieberman|Can Machines Replicate Human Behavior From the Outside by Matthew D. Lieberman]] > "The only viable approach to construct a machine that has the attributes of the human brain is to copy the neuronal circuits underlying thinking." > **— Leo M. Chalupa**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Neural Interfaces/Humanlike Machines Must Copy Neuronal Circuits by Leo M. Chalupa|Humanlike Machines Must Copy Neuronal Circuits by Leo M. Chalupa]] > "Perhaps individual machines may never "think" in a way that resembles individual human consciousness as we understand it." > **— Rebecca MacKinnon**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Consciousness/Machines May Never Think Like Human Consciousness by Rebecca MacKinnon|Machines May Never Think Like Human Consciousness by Rebecca MacKinnon]] > "Practically, it is only the long-term evolution of information technology, from the earliest representations and symbolic constructs to the most advanced current artificial brain, that allows the advancement of thought." > **— Timothy Taylor**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Evolution/Technology Expands the Space of Thought by Timothy Taylor|Technology Expands the Space of Thought by Timothy Taylor]] > "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]] ## 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.