Rohan Paul (@rohanpaul_ai)
이 블로그 글은 지능을 '고차적 새로움에 의한 영향 극대화(impact maximization)'로 설명하며, 대규모 스파이킹 신경망에서 헵비안 연합 학습(Hebbian associative learning)이 그러한 영향이나 목표 달성 능력을 만들어낼 수 있다고 주장한다. 다소 오래된 글이지만 흥미로운 이론적 개념과 신경계 모델 관점을 제시한다.
https://x.com/rohanpaul_ai/status/2009108097151930432
#neuroscience #hebbianlearning #spikingnn #aitheory
Rohan Paul (@rohanpaul_ai) on X
Some interesting concepts proposed in this blog (little old but interesting).
Intelligence is described as impact maximization through higher order novelty.
The author argues that Hebbian associative learning in a large spiking neural network can produce impact or
Understanding Hebbian learning in Hopfield networks
Hopfield networks, a form of recurrent neural network (RNN), serve as a fundamental model for understanding associative memory and pattern recognition in computational neuroscience. Central to the operation of Hopfield networks is the Hebbian learning rule, an idea encapsulated by the maxim ‘neurons that fire together, wire together’. In this post, we explore the mathematical underpinnings of Hebbian learning within Hopfield networks, emphasizing its role in pattern recognition.
sayzard
Fabrizio Musacchio