Machine Learning Street Talk (MLST)

#75 - Emergence [Special Edition] with Dr. DANIELE GRATTAROLA

34 snips
Apr 29, 2022
Dr. Daniele Grattarola, a postdoctoral researcher at EPFL, specializes in graph neural networks and protein design. He dives deep into the captivating concept of emergence, comparing weak and strong emergence in complex systems. The discussion touches on how simple rules in cellular automata can lead to complex, intelligent behaviors. They also explore the philosophical implications of emergence, the predictability of complex systems, and how these ideas relate to advanced applications in artificial intelligence and protein folding.
Ask episode
AI Snips
Chapters
Books
Transcript
Episode notes
INSIGHT

Emergent Behavior

  • Simple entities operating in an environment can exhibit complex collective behaviors, known as emergent properties.
  • These properties are scale-dependent and arise from interactions between components or with the environment.
INSIGHT

Computational Irreducibility of CAs

  • Emergent behavior is computationally irreducible; there are no shortcuts besides simulation.
  • This applies to discrete and continuous cellular automata.
INSIGHT

Weak Emergence

  • Weak emergence arises from low-level interactions, becoming observable at larger system scales.
  • Predicting emergent behavior is difficult due to exponentially increasing interactions between components.
Get the Snipd Podcast app to discover more snips from this episode
Get the app