How neuroscience enables better Artificial Intelligence design

Here's another one of my "learning nerdism" shares. I love this kind of overlap.

I'm sharing this from the daily Bing News for Professionals newsletter Industry Spotlights I get via email. Much of what I wrote below is paraphrasing and directly quoted from the original story. I encourage you to read all of Justin Lee's article yourself at: https://medium.com/swlh/how-neuroscience-enables-better-artificial-intelligence-design-5d254098470b

Summary

"one element that is often overlooked is a combination of science and engineering: the use of both theoretical and experimental neuroscience. Neuroscience has made several pivotal contributions to AI development ... 'The fundamental questions cognitive neuroscientists and computer scientists seek to answer are similar,' says Aude Oliva of MIT. 'They have a complex system made of components — for [neuroscience], it’s called neurons, and for [AI], it’s called units.'"

Why this matters to us as learning professionals 

"To build super-intelligent machines, we must gain a deeper understanding of the human brain. Equally, exploring AI can help us gain a better understanding on what’s going on in our own heads."

Definitions & How they are connected

1. Cognitive science - an offshoot of human psychology and is literally the study of cognition, or thought. It includes language, problem-solving, decision-making, and perception, especially consciously aware understanding. Cognitive science started with those higher-level behavioral traits that were observable or testable and asked what is going on inside the mind or brain to make that possible.
2. Neuroscience - a strand of biology based on the study of the anatomy and physiology of the human brain, including structures, neurons and molecules. It studies how the brain works in terms of mechanics, functions and systems in order to create recognizable behaviors. 
3. Artificial Neural Network (ANN) - a simplified, computational model of a biological brain ... a way of detecting patterns.
4. Deep Learning - (a subset of AI) is mostly [about] architecture as opposed to its resemblance to the human brain.

Cognitive theories and AI relationship/design

1. Associationism
2. Associative structures
3. Connectionism

AI Limitations (+1 for humans!)

1. It's "forgetful" - "relearning a new task often erases the established connections. This leads to catastrophic forgetting: when the AI learns the new task, it overwrites the previous one."
2. It lacks the ability to interact through sensory and motor experiences. "It's the sort of common sense that humans have, an intuition about the world that’s hard to describe but extremely useful for the daily problems we face."
3. An inability to imagine or innovate - "Imagination and innovation relies on models we’ve already built about our world, and extrapolating new scenarios from them."

Where neuroscience & AI intersect

"while logic-based methods and theoretical mathematical models have dominated traditional approaches to AI, neuroscience can complement these approaches by identifying classes of biological computation that could be critical to cognitive functions." In short, we can take what we know about our brains to inform new ways to design AI. 

Consider biological and cognitive functions of: 

• Pruning - "the fact that humans will forget things that don’t matter to them." 
• Learning transfer - "To be able to process unique situations, AI agents need to be able to reference existing knowledge to make informed decisions." People can do this very well, learning from one seemingly unrelated situation and transferring that learning across domains to be used in a new situation. Machines struggle with this, although "a new type of network architecture called a ‘progressive network’ can use knowledge from one video game to determine another." 
• "This suggests there is massive potential for AI research to learn from neuroscience."

Neuroscience also benefits from AI research. 

• Consider "reinforcement learning. "Modern neuroscience, for all its powerful imaging tools and optogenetics, has only just begun unraveling how neural networks support higher intelligence."

In conclusion

"This mutual investment is crucial for progress in both fields.

1. "Researchers can explore neuroscience in the quest to develop AI and push forward scientific discovery. And
2. "examining AI in correlation with neuroscience could help us explore some of life’s greatest mysteries, such as creativity, imagination, dreams and consciousness."