Long Short-Term Memory

Learning long-term dependencies with gradient descent is difficult

1994 • 7,520 citations

Generalization of back-propagation to recurrent neural networks

1987 • 938 citations

Generalization of backpropagation with application to a recurrent gas market model

1988 • 927 citations

LSTM can Solve Hard Long Time Lag Problems

1996 • 743 citations

Learning long-term dependencies in NARX recurrent neural networks

1996 • 736 citations

Learning State Space Trajectories in Recurrent Neural Networks

1989 • 676 citations

Gradient calculations for dynamic recurrent neural networks: a survey

1995 • 593 citations

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

1990 • 589 citations

A time-delay neural network architecture for isolated word recognition

1990 • 587 citations

Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks

1994 • 529 citations

Finite State Automata and Simple Recurrent Networks

1989 • 466 citations

Gradient-based learning algorithms for recurrent networks and their computational complexity

1995 • 422 citations

Learning Complex, Extended Sequences Using the Principle of History Compression

1992 • 402 citations

A learning rule for asynchronous perceptrons with feedback in a combinatorial environment

1990 • 277 citations

Dynamics and architecture for neural computation

1988 • 192 citations

Induction of Finite-State Languages Using Second-Order Recurrent Networks

1992 • 149 citations

The Recurrent Cascade-Correlation Architecture

1990 • 147 citations

Bifurcations in the learning of recurrent neural networks

2003 • 132 citations

Adaptive neural oscillator using continuous-time back-propagation learning

1989 • 131 citations

Induction of Multiscale Temporal Structure

1991 • 131 citations

A Fixed Size Storage O(n³) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks

1992 • 113 citations

A Local Learning Algorithm for Dynamic Feedforward and Recurrent Networks

1989 • 85 citations

A Theory for Neural Networks with Time Delays

1990 • 63 citations

Contrastive Learning and Neural Oscillations

1991 • 56 citations

EXPERIMENTAL COMPARISON OF THE EFFECT OF ORDER IN RECURRENT NEURAL NETWORKS

1993 • 50 citations

LEARNING SEQUENTIAL STRUCTURE WITH THE REAL-TIME RECURRENT LEARNING ALGORITHM

1989 • 37 citations

Credit Assignment through Time: Alternatives to Backpropagation

1993 • 34 citations

Holographic Recurrent Networks

1992 • 34 citations

Learning Unambiguous Reduced Sequence Descriptions

1991 • 33 citations

Learning Sequential Tasks by Incrementally Adding Higher Orders

1992 • 32 citations

Guessing can Outperform Many Long Time Lag Algorithms

1996 • 19 citations

Time Warping Invariant Neural Networks

1992 • 16 citations

Language Induction by Phase Transition in Dynamical Recognizers

1990 • 3 citations

Deleted Work

1955 • 0 citations