Learn More
In this paper the efficiency of recurrent neural network implementations of m-state finite state machines will be explored. Specifically, it will be shown that the node complexity for the unrestricted case can be bounded above by 0 (fo). It will also be shown that the node complexity is 0 (y'm log m) when the weights and thresholds are restricted to the set(More)
We describe a software self-checking mechanism designed to improve the tamper resistance of large programs. The mechanism consists of a number of testers that redundantly test for changes in the executable code as it is running and report modifications. The mechanism is built to be compatible with copy-specific static watermarking and other(More)
It has previously been shown that gradient-descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long-term dependencies, i.e. those problems for which the desired output depends on inputs presented at times far in the past. We show that the long-term dependencies problem is lessened for a class of architectures(More)
We describe several new bottom-up approaches to problems in role engineering for Role-Based Access Control (RBAC). The salient problems are all NP-complete, even to approximate, yet we find that in instances that arise in practice these problems can be solved in minutes. We first consider role minimization, the process of finding a smallest collection of(More)
We present two approaches to the analysis of the relationship between a recurrent neural network (RNN) and the nite state machine M the network is able to exactly mimic. First, the network is treated as a state machine and the relationship between the RNN and M is established in the context of algebraic theory of automata. In the second approach, the RNN is(More)
It has recently been shown that gradient descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long-term dependencies. In this paper we explore this problem for a class of architectures called NARX networks, which have powerful representational capabilities. Previous work reported that gradient descent learning(More)
Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with(More)
Distribution of content, such as music, remains one of the main drivers of P2P development. Subscription-based services are currently receiving a lot of attention from the content industry as a viable business model for P2P content distribution. One of the main problems that such services face is that users may choose to redistribute content outside the(More)
Product units provide a method of automatically learning the higher-order input combinations required for eecient learning in neural networks. However, we show that problems are encountered when using backpropagation to train networks containing these units. This paper examines these problems, and proposes some atypical heuristics to improve learning. Using(More)