Unsupervised RNNGs perform similarly to supervised ones in language modeling and grammar induction.
problem Training RNNGs requires annotated data, which is costly.
method Amortized variational inference with a neural CRF parser.
result Unsupervised RNNGs achieve comparable performance to supervised ones.
Unified recurrent networks reveal differences in complexity levels of grammars.
problem Understanding the complexity and behavior of recurrent networks.
method Connecting recurrent networks with deterministic finite automata and formal grammars.
result Unified recurrent networks improve performance and match grammars from different complexity levels.
The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured. While most prior work contributes to verifying feed-forward networks, little has been explored for verifyin…
Method extracts knowledge from LSTM for sequence validation.
problem Validating sequences generated by unknown automata.
method Clustering hidden states to build a corresponding automaton.
result Automaton accurately predicts sequence validity.
Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more tokens than a natural language sentence, and thus it may be inappropriate for RN…
We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invarian…
Proposes a method to train neural networks directly on compressed text data.
problem Training neural networks on compressed text data without decompression.
method Introduces composer modules to encode symbols from grammar compression rules into vector representations.
result Demonstrates that the proposed method can achieve both memory and computational efficiency while maintaining moderate performance.
To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors,…
Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i) in the machine learning field methods such as (hidden) Markov models and recurr…
Tree-Transformer improves grammar correction in code and natural language.
problem Grammar correction in tree-structured data.
method Tree-Transformer neural network architecture for tree-structured data.
result Significant improvement in grammar correction accuracy.
Recurrent Neural Networks (RNN) are a type of statistical model designed to handle sequential data. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from the previous symbols. With existing RNN architectures, each symbol is processed using only information from th…
Improved AutoML performance with a pipeline grammar and pre-trained model.
problem Automatic machine learning by pipeline synthesis.
method Model-based reinforcement learning and pipeline grammar.
result Improved performance on AutoML benchmark datasets.
Capsule networks improve at detecting changes in compositionality with routing.
problem Capsule networks struggle with detecting changes in compositionality.
method Introduced a loss function based on routing entropy to improve compositionality.
result Capsule networks with the new loss function better detect changes in compositionality.
Proposes a framework for compositional generalization in language models.
problem Lack of compositional generalization in neural networks compared to humans.
method Introduces Generalized Grammar Rules (GGRs) for transduction tasks, formalizing symmetry-based constraints.
result Framework enables models to generalize compositionally, similar to human learning.
Unified model improves coherence tasks, especially local contexts.
problem Existing neural coherence models struggle with local context tasks.
method Unified neural framework integrating grammar, relations, and patterns.
result Unified model outperforms existing models significantly.
Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.
problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.
Molecular optimization aims to discover novel molecules with desirable properties. Two fundamental challenges are: (i) it is not trivial to generate valid molecules in a controllable way due to hard chemical constraints such as the valency conditions, and (ii) it is often costly to evaluate a property of a novel molecu…
The task of translating between programming languages differs from the challenge of translating natural languages in that programming languages are designed with a far more rigid set of structural and grammatical rules. Previous work has used a tree-to-tree encoder/decoder model to take advantage of the inherent tree s…
AlphaCFG discovers alpha factors using grammar-guided search.
problem Discovering formulaic alpha factors in finance.
method AlphaCFG uses a grammar-based framework to define and discover alpha factors with syntactic and semantic constraints.
result AlphaCFG outperforms state-of-the-art methods in trading profitability and efficiency.
New grammar model learns sentence structure with latent variables.
problem Grammar induction for sentences with complex dependencies.
method Compound probabilistic context-free grammar with latent variables, variational inference.
result Effective unsupervised parsing compared to state-of-the-art methods.
Probabilistic grammars improve equation discovery from data.
problem Discovering scientific laws from data using equations.
method Proposed probabilistic context-free grammars to encode soft constraints and a Monte-Carlo algorithm.
result Probabilistic grammars lead to more efficient equation discovery.
Interneurons improve learning in neural networks by accelerating convergence.
problem Rapid adaptation to changing input statistics in neural networks.
method Two mathematically tractable recurrent linear neural networks were compared: one with direct recurrent connections and the other with interneurons that mediate recurrent communication.
result The network with interneurons converges more quickly than the network with direct recurrent connections, scaling logarithmically with initialization spectrum.
QRPNNs use quaternion-valued recurrent correlation neural networks to solve cross-talk issues.
problem Cross-talk problem in QRCNNs.
method Combining non-local projection learning with QRCNNs.
result QRPNNs exhibit greater storage capacity and noise tolerance.
A new framework generates large hierarchical search spaces for neural architectures.
problem Discovering neural architectures from simple blocks is hard.
method Context-free grammars for a unified, scalable search space.
result Efficiently searches over complete architectures, outperforming existing methods.
RecNets use RNNs to process image channels in a compact, recurrent way.
problem Creating efficient neural network architectures for computer vision.
method Introducing RecNets with CRC layers that simulate recurrent processing of image channels.
result RecNets achieve superior size-accuracy trade-off compared to other compact models.
einspace expands NAS search space to include diverse neural architectures.
problem NAS results are often limited to existing structures; new designs are rare.
method einspace uses a probabilistic context-free grammar to create a versatile search space.
result einspace discovers novel and improved architectures, including convolutions and attention.
Algorithm discovers dynamic cell structures for better neural network performance.
problem Finding optimal neural network architectures for diverse data samples and time steps.
method Combines recurrent and recursive neural networks to dynamically search for customized cell structures.
result Achieves better prediction accuracy compared to existing models.
Paper presents FPGA implementation for efficient recurrent neural networks.
problem Implementing recurrent neural networks on FPGAs for low latency.
method Developed hls4ml framework to implement LSTM and GRU layers.
result Demonstrated effective designs for both small and large models.
Scalable verifier for recurrent neural networks using polyhedral abstractions.
problem Certifying the correctness of recurrent neural networks.
method Combining sampling, optimization, and Fermat's theorem for polyhedral abstractions; gradient descent for refinement.
result Successfully verified challenging recurrent models in various domains.
This paper analyzes the generalization risk of unrolled neural networks using Stein's Unbiased Risk Estimator.
problem Analyzing the generalization risk of unrolled neural networks and its relationship to network design and train sample size.
method Using Stein's Unbiased Risk Estimator (SURE), the paper analyzes the generalization risk with bias and variance components for recurrent unrolled networks, focusing on the degrees-of-freedom (DOF) component and the trace of the end-to-end network Jacobian.
result DOF is well-approximated by the weighted path sparsity of the network under incoherence conditions on the trained weights, and DOF increases with train sample size and converges to the generalization risk for both recurrent and non-recurrent schemes.
AG-RL uses action grammars to improve reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Integrates action grammars into reinforcement learning algorithms to enhance performance.
result Significant improvement in performance across multiple Atari games.
Bayesian approach improves neural network recurrence.
problem Improving neural network recurrence mechanisms.
method Introducing Bayesian recurrence relations and gates.
result Bayesian approach can perform as well as or better than conventional recurrent networks.
End-to-end training of recurrent neural networks for biological sequences.
problem Training recurrent neural networks for biological sequence classification.
method Generalized convolutional kernel networks with recurrent structures.
result Outperforms existing methods for protein classification tasks.
Time series forecasting is difficult. It is difficult even for recurrent neural networks with their inherent ability to learn sequentiality. This article presents a recurrent neural network based time series forecasting framework covering feature engineering, feature importances, point and interval predictions, and for…
Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse Variational Dropout eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique …
SIS-RNN improves model flexibility for sequential data.
problem Limited expressive power of existing stochastic RNNs.
method Semi-implicit variational inference for implicit latent representations.
result SIS-RNN outperforms existing methods in various tasks.
Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs). We propose a simp…
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The c…
RANP improves neural processes for sequential data.
problem Capturing temporal order and recurrent structure from sequential data.
method Incorporated ANP into a recurrent neural network.
result RANP outperforms NPs and LSTMs in 1D regression and autonomous-driving tasks.
Optimal stock price prediction model using recurrent neural networks with RMSprop optimizer.
problem Stock price prediction using neural networks.
method Comparison of fully connected, convolutional, and recurrent architectures; inclusion of three optimization techniques.
result Single layer recurrent neural network with RMSprop optimizer produces optimal results with validation and test MAE of 0.0150 and 0.0148 respectively.
Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a re…
Paper presents RGNN for better graph node representation learning.
problem Node representation learning with graph neural networks.
method Recurrent Graph Neural Network (RGNN) with recurrent units.
result RGNN achieves state-of-the-art results on three benchmarks.
Develops inference combinators for probabilistic programs using neural networks.
problem Creating efficient proposals for probabilistic program inference.
method Inference combinators using neural network parameterization of proposals.
result Correct by construction variational methods tailored to specific models.
Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads…
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation b…
New method prunes recurrent networks efficiently, improving performance.
problem Pruning recurrent neural networks (RNNs) is challenging and often leads to poor performance.
method Data-efficient pruning objective derived from the spectrum of the recurrent Jacobian.
result 95% sparse GRUs significantly improve on existing baselines.
Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.
problem Stability of internal states in recurrent neural networks trained on regular languages.
method Empirical study with analysis of network activation and transitions between states.
result Recurrent neural networks trained on regular languages can recover from random perturbations and maintain stable states.
Dual neural network architecture improves accuracy and interpretability.
problem Improving neural network interpretability and accuracy.
method Stacked recurrent and feedforward layers, binary activation function.
result Binary activation leads to simpler, more interpretable models with higher accuracy.