Gumbel-Softmax provides a continuous relaxation of categorical sampling that anneals to discrete samples for gradient-based optimization.
Hierarchical Multiscale Recurrent Neural Networks
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Learning both hierarchical and temporal representation has been among the long-standing challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can actually capture the temporal dependencies by discovering the latent hierarchical structure of the sequence. In this paper, we propose a novel multiscale approach, called the hierarchical multiscale recurrent neural networks, which can capture the latent hierarchical structure in the sequence by encoding the temporal dependencies with different timescales using a novel update mechanism. We show some evidence that our proposed multiscale architecture can discover underlying hierarchical structure in the sequences without using explicit boundary information. We evaluate our proposed model on character-level language modelling and handwriting sequence modelling.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Dilated RNN wave functions induce power-law correlations for the critical 1D transverse-field Ising model and the Cluster state, unlike the exponential decay of conventional RNN ansatze.
SMT reduces RNN training to supervised learning on memory transitions (m_t, x_{t+1}) to m_{t+1} obtained from a Transformer encoder, enabling time-parallel training with O(1) gradient paths.
Compressive Transformer sets new records on WikiText-103 (17.1 ppl) and Enwik8 (0.97 bpc) via memory compression and introduces the PG-19 long-range language benchmark.
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
SHARP separates memory accumulation from pattern recognition and uses accelerated offline replay of structured traces to achieve exponentially growing effective context at linear compute cost while learning non-stationary streams.
ARMIN introduces auto-addressing via hidden states and a novel RNN cell to produce a lighter recurrent memory network with lower overhead than existing MANNs or vanilla LSTMs.
citing papers explorer
-
Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States
Dilated RNN wave functions induce power-law correlations for the critical 1D transverse-field Ising model and the Cluster state, unlike the exponential decay of conventional RNN ansatze.