Show

Connectionism

Week of: 
February 17, 2008
What is it: 

Does the human mind work like a computer? If so, what kind of computer? A theory known as connectionism offers a revolutionary perspective on these issues. Ken and John delve into cutting-edge cognitive science with Jay McClelland from Stanford University, an architect of the connectionist view.

Listening Notes: 

Connectionism is an innovative theory about how the mind works, and its based on the way the brain and its neurons work.  According to the theory, although each of our individual neurons have very little computational power on their own, they have tremendous computational power when organized in combination with one another.  Ken and John are joined by guest, James McClelland to discuss the strengths and weaknesses of the connectionist model.  

Understanding the way we learn is an age old problem in psychology and according to McClelland, questions surrounding learning motivate the connectionist position.  The old-fashioned, artificial intelligence (AI) model of learning stated that because our brains structured in a particular way the from the day we are born, our thoughts must be pre-structured in particular kinds of ways too.  For example human language, it was argued, is pre-specified in our genes.  Unfortunately, McClelland argues, this AI approach does not make contact with the fact that the way we talk and interact is shaped by our experiences and the things we’ve learned.  

McClelland explains that connectionism took hold in the early 1980s when scientists began making better computer models of neurons and way neurons work together in systems.  The connectionist theory of learning is that neuron’s are interconnected, and when neuron’s change connections the brain system learns.  

John questions McClelland about the relation between connectionism and an older theory, associationism.  McClelland agrees that connectionism is a modern version of the same idea but with one key distinction.  Associationism is the theory that associations are formed in our minds when two events occur together; we learn by contiguity, and when something new happens we understand it by generalizing and approximating according to our previous association.  According to McClelland, the weakness in the associationist argument is the fact that it doesn’t account for how we learn to re-associate events in our minds.  We don’t just approximate to understand new information, we learn new information.  The connectionist system learns by adjusting the connections between neurons.  

John, Ken and McClelland continue the conversation.  They discuss practical applications for connectionist systems in computer science, the effect our emotions have on learning, and some objections to connectionism.

  • Roving Philosophical Reporter April Demboski (seek to 5:00).  April talks to us about talking to computers.

James J. McClelland, Lucie Stern Professor and Chair, Department of Psychology Director, Center for Mind, Brain and Computation, Stanford University

Related Resources: 

Internet Resources

  • "Connectionism: An Introduction," Consortium on Mind/Brain Science Instruction.  (A basic introduction to connectionism divided into three parts.  The first begins with "what is connectionism?"  The second and third sections cover unit behavior and network behavior, respectively.)

Books

Get Philosophy Talk

Radio

Sunday at 10am, PST, KALW, 91.7 FM, Local Public Radio, San Francisco

Podcast

Individual Downloads  via CdBaby or Itunes.  Multipacks and The Complete Philosophy Talk via Iamplify

John Perry and Ken Taylor

Continue the Conversation

Sidebar Menu

Upcoming Shows

  • April 5 : The Nature of Wilderness
    Nowadays we think of wilderness as a fully natural environment that contrasts sharply with the designed and constructed environments in which we...
  • April 12 : The Art of Non-Violence
    We all hope for peace. Yet in the face of violence, it often seems the only recourse is more violence. Advocates of non-violence claim it’s not...
  • April 19 : Economics - Science or Cult?
    With the recent global economic crisis, many people wonder if our economic policies are built on sound principles or on dubious, unscientific claims...
  • April 26 : When Democracies Torture
    Torture is prohibited under international law and is widely considered a human rights violation. But despite the fact that 157 countries ratified the...
  • May 3 : Reincarnation - Past Lives, Future Selves
    According to Buddhist tradition, all people must suffer illness, aging, and death. Yet the universe is seen as a vast living entity, in which cycles...

Support Philosophy Talk

DONATE TODAY

Philosophy Talk relies on the support of listeners like you to stay on the air and online. Any contribution, large or small, helps us produce intelligent, reflective radio that questions everything, including our most deeply-held beliefs about science, morality, culture, and the human condition. Make your tax-deductible contribution now through Stanford University's secure online donation page. Thank you for your support, and thank you for thinking!