Machine, Learning, 1951

Marvin Minsky engineered the first known artificial neural network, in which “rats” represented as lights learned to solve a maze.

Written byJef Akst
| 3 min read
the scientist foundations original the first artifical intelligence

Register for free to listen to this article
Listen with Speechify
0:00
3:00
Share

ABOVE: The SNARC machine included 40 artificial neurons (one pictured), which were interconnected via a plugboard and held in racks in a contraption about the size of a grand piano. At one end of the neuron was a potentiometer (bar on far right), a sort of volume knob that could adjust the probability that an incoming signal would result in an outgoing signal. If the neuron did fire, a capacitor (red) on the other end of the neuron retained a memory of the firing for a few seconds. If the system was “rewarded”—either by the researchers pushing a button or an electrical signal from an outside circuit—a chain connected to the volume knobs for all 40 neurons would crank. This would cause the volume knob to increase the future probability of the neuron firing, but only if a magnetic clutch had been engaged by a recent firing.
COURTESY OF MARGARET MINSKY

...

Interested in reading more?

Become a Member of

The Scientist Logo
Receive full access to digital editions of The Scientist, as well as TS Digest, feature stories, more than 35 years of archives, and much more!
Already a member? Login Here

Related Topics

Meet the Author

  • Jef (an unusual nickname for Jennifer) got her master’s degree from Indiana University in April 2009 studying the mating behavior of seahorses. After four years of diving off the Gulf Coast of Tampa and performing behavioral experiments at the Tennessee Aquarium in Chattanooga, she left research to pursue a career in science writing. As The Scientist's managing editor, Jef edited features and oversaw the production of the TS Digest and quarterly print magazine. In 2022, her feature on uterus transplantation earned first place in the trade category of the Awards for Excellence in Health Care Journalism. She is a member of the National Association of Science Writers.

    View Full Profile

Published In

May 2019 The Scientist Issue
May 2019

AI Tackles Biology

How machine learning will revolutionize science and medicine.

Share
Illustration of a developing fetus surrounded by a clear fluid with a subtle yellow tinge, representing amniotic fluid.
January 2026

What Is the Amniotic Fluid Composed of?

The liquid world of fetal development provides a rich source of nutrition and protection tailored to meet the needs of the growing fetus.

View this Issue
Human-Relevant In Vitro Models Enable Predictive Drug Discovery

Advancing Drug Discovery with Complex Human In Vitro Models

Stemcell Technologies
Redefining Immunology Through Advanced Technologies

Redefining Immunology Through Advanced Technologies

Ensuring Regulatory Compliance in AAV Manufacturing with Analytical Ultracentrifugation

Ensuring Regulatory Compliance in AAV Manufacturing with Analytical Ultracentrifugation

Beckman Coulter Logo
Skip the Wait for Protein Stability Data with Aunty

Skip the Wait for Protein Stability Data with Aunty

Unchained Labs

Products

Sino Biological Logo

Sino Biological's Launch of SwiftFluo® TR-FRET Kits Pioneers a New Era in High-Throughout Kinase Inhibitor Screening

SPT Labtech Logo

SPT Labtech enables automated Twist Bioscience NGS library preparation workflows on SPT's firefly platform

nuclera logo

Nuclera eProtein Discovery System installed at leading Universities in Taiwan

Brandtech Logo

BRANDTECH Scientific Introduces the Transferpette® pro Micropipette: A New Twist on Comfort and Control