Episode 28: Psychedelic Artificial Neural Networks

Cognitive philosophers Richard Brown and Pete Mandik examine recent claims by Google researchers to have implemented dreams, imagery, and hallucinations in artificial neural networks. The images created by these artificial systems are kind of cool, but can anything at all be learned from such projects about how the mind or brain actually functions? Richard and Pete move from there to debate connectionism, AI, and rationalist vs. empiricist methodologies in the philosophy of cognitive science. Special prize for the first listener to correctly identify all three of the neuroscientists that Pete misidentifies! #deepdream

(The audio for this episode is drawn from the video chat viewable here: @YouTube.)

• "Inceptionism: Going Deeper into Neural Networks" @GoogleResearchBlog
• Jifeng Dai, Yang Lu, Ying-Nian Wu “Generative Modeling of Convolutional Neural Networks” 
• Jonas Degrave "LSD neural net: Large Scale Deep neural net visualizing top level features" 
• Sidney Lehky & Terrence Sejnowski "Network model of shape-from-shading: neural function arises from both receptive and projective fields" 
• "Planarian Regeneration Model Discovered by Artificial Intelligence" @TuftsNow 
• David Papineau "The Rise of Physicalism"