… Using a prediction task, a simple recurrent network (SRN) is trained on multiclausal …
Principal component analysis of the hidden unit activation patterns reveals that the network solves …

… I have tried to show that simple recurrent networks do in fact generalize to novel inputs
and to novel uses of inputs. It is true that networks are subject—as are we—to perceptual …

… recurrent neural networks more generally) are feedforward (Norris, 1993), this is not the case.
Feedforward networks … the sense normally implied for networks with feedback connections …

… We have also shown that the simple recurrent network is able to encode information about
long-distance contingencies as long as information about critical past events is relevant at …

… We have also shown that the simple recurrent network is able to encode information about
contingencies that are not local to a given letter and its immediate predecessor, such as those …

… In response to Rodriguez’s recent article (2001), we compare the performance of simple
recurrent nets and long short-term memory recurrent nets on context-free and context-sensitive …

… This paper shows that a simple recurrent connectionist network (SRN) (Elman, 1990) might
provide an insight into this problem. An SRN is first trained on two micro-languages and the …

… network architectures. In this paper, we propose a simpler solution that use recurrent neural
networks … matrix or its scaled version to initialize the recurrent weight matrix. We find that our …

… : (i) a neural network structure referred as simple recurrent neural network (SRNN), (ii) a …
A comparison between the SRNN and some other neural network structures, based on the …

… networks are also referred to as simple recurrent networks in … recurrent networks are among
the most popular of recurrent … Simple recurrent networks can be extended to fully recurrent …