Lower bound for connectivity in local-learning neural networks
نویسندگان
چکیده
منابع مشابه
Reinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملMonotone depth lower bound for st connectivity
In Lecture 2, we saw how communication complexity lower bounds yield lower bounds for circuit depth. In particular, we showed that for any function f , D(KWf ) = depth(f) and D(KW f ) = depth (f), where KWf denotes the Karchmer-Wigderson game on f . Using this, we showed that monotone circuits for matching require Ω(n) depth. In this lecture we will show that circuits solving directed s-t conne...
متن کاملA New Lower Bound for Completion Time Distribution Function of Stochastic PERT Networks
In this paper, a new method for developing a lower bound on exact completion time distribution function of stochastic PERT networks is provided that is based on simplifying the structure of this type of network. The designed mechanism simplifies network structure by arc duplication so that network distribution function can be calculated only with convolution and multiplication. The selection of...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملLocal learning algorithm for optical neural networks.
An anti-Hebbian local learning algorithm for two-layer optical neural networks is introduced. With this learning rule, the weight update for a certain connection depends only on the input and output of that connection and a global, scalar error signal. Therefore the backpropagation of error signals through the network, as required by the commonly used back error propagation algorithm, is avoide...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Complexity
سال: 1988
ISSN: 0885-064X
DOI: 10.1016/0885-064x(88)90022-2