Tootfinder

This https://arxiv.org/abs/2505.22083 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Hyperbolic recurrent neural network as the first type of non-Euclidean neural quantum state ansatz
In this work, we introduce the first type of non-Euclidean neural quantum state (NQS) ansatz, in the form of the hyperbolic GRU (a variant of recurrent neural networks (RNNs)), to be used in the Variational Monte Carlo method of approximating the ground state wavefunction for quantum many-body systems. In particular, we examine the performances of NQS ansatzes constructed from both conventional or Euclidean RNN/GRU and from hyperbolic GRU in the prototypical settings of the one- and two-dimensi…

Dense Associative Memory in a Nonlinear Optical Hopfield Neural Network
Khalid Musa, Santosh Kumar, Michael Katidis, Yu-Ping Huang
https://arxiv.org/abs/2506.07849

Dense Associative Memory in a Nonlinear Optical Hopfield Neural Network
Modern Hopfield Neural Networks (HNNs), also known as Dense Associative Memories (DAMs), enhance the performance of simple recurrent neural networks by leveraging the nonlinearities in their energy functions. They have broad applications in combinatorial optimization, high-capacity memory storage, deep learning transformers, and correlated pattern recognition. Thus far, research on DAMs has been primarily theoretical, with implementations limited to CPUs and GPUs. In this work, for the first ti…

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
https://arxiv.org/abs/2507.07996 https://arxiv.org/pdf/2507.07996 https://arxiv.org/html/2507.07996
arXiv:2507.07996v1 Announce Type: new
Abstract: Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This compositional space greatly expands the scope of existing works on looped/recurrent pretrained modules, layer pruning, or early-exit networks. We develop a Monte Carlo Tree Search (MCTS) protocol to explore and identify the optimal CoLa for each sample from math and commonsense reasoning benchmarks. Compared to a static model of a fixed depth, CoLa allows shortcut paths (fast thinking), recurrence of the same layer(s) (slow thinking), and combining both, offering more flexible, dynamic architectures for different inputs. We conduct an extensive analysis of the MCTS-optimized CoLa, which leads to two key findings: (1) For >75% of samples with correct predictions by the original LLM, we can find shorter CoLa, suggesting a large space for improving inference efficiency; (2) For >60% of samples with originally incorrect predictions, we can identify CoLa achieving correct predictions, suggesting a large space of performance enhancement. Our results highlight the shortcomings of using a fixed architecture of pre-trained LLMs for inference on different samples and pave the way to unlock the generalization power of test-time depth adaptation.
toXiv_bot_toot

This https://arxiv.org/abs/2506.05588 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

A Linear Generative Framework for Structure-Function Coupling in the Human Brain
Sam Frank Kelemen, Joaqu\'in G\~oni, S\'ergio Pequito, Arian Ashourvan
https://arxiv.org/abs/2507.06136

A Linear Generative Framework for Structure-Function Coupling in the Human Brain
Brain function emerges from coordinated activity across anatomically connected regions, where structural connectivity (SC) -- the network of white matter pathways - provides the physical substrate for functional connectivity (FC) -- the correlated neural activity between brain areas. While these structural and functional networks exhibit substantial overlap, their relationship involves complex, indirect mechanisms, including the dynamic interplay of direct and indirect pathways, recurrent netwo…

This https://arxiv.org/abs/2406.03456 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Recurrent neural chemical reaction networks that approximate arbitrary dynamics
Many important phenomena in biochemistry and biology exploit dynamical features such as multi-stability, oscillations, and chaos. Construction of novel chemical systems with such rich dynamics is a challenging problem central to the fields of synthetic biology and molecular nanotechnology. In this paper, we address this problem by putting forward a molecular version of a recurrent artificial neural network, which we call recurrent neural chemical reaction network (RNCRN). The RNCRN uses a modul…

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
Sebastian Murgul, Moritz Reiser, Michael Heizmann, Christoph Seibert
https://arxiv.org/abs/2506.22237

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
In this paper, we present a neural network approach for synchronizing audio recordings of human piano performances with their corresponding loosely aligned MIDI files. The task is addressed using a Convolutional Recurrent Neural Network (CRNN) architecture, which effectively captures spectral and temporal features by processing an unaligned piano roll and a spectrogram as inputs to estimate the aligned piano roll. To train the network, we create a dataset of piano pieces with augmented MIDI fil…

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Rishona Daniels, Duna Wattad, Ronny Ronen, David Saad, Shahar Kvatinsky
https://arxiv.org/abs/2506.05588

Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC systems benefit from their dynamic properties, which make them ideal for reservoir construction. However, achieving high performance in memristor-based RC remains challenging, as it critically depends on the input preprocessing method and reservoir size. Despite …

ChemReservoir -- An Open-Source Framework for Chemically-Inspired Reservoir Computing
Mehmet Aziz Yirik, Jakob Lykke Andersen, Rolf Fagerberg, Daniel Merkle
https://arxiv.org/abs/2506.04249

ChemReservoir -- An Open-Source Framework for Chemically-Inspired Reservoir Computing
Reservoir computing is a type of a recurrent neural network, mapping the inputs into higher dimensional space using fixed and nonlinear dynamical systems, called reservoirs. In the literature, there are various types of reservoirs ranging from in-silico to in-vitro. In cheminformatics, previous studies contributed to the field by developing simulation-based chemically inspired in-silico reservoir models. Yahiro used a DNA-based chemical reaction network as its reservoir and Nguyen developed a D…

This https://arxiv.org/abs/2506.01226 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
We study parameterizations of stabilizing nonlinear policies for learning-based control. We propose a structure based on a nonlinear version of the Youla-Kučera parameterization combined with robust neural networks such as the recurrent equilibrium network (REN). The resulting parameterizations are unconstrained, and hence can be searched over with first-order optimization methods, while always ensuring closed-loop stability by construction. We study the combination of (a) nonlinear dynamics, …

Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
Jake McNaughton, Mohamed Hibat-Allah
https://arxiv.org/abs/2507.18700 https://arxiv.…

Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
Neural-network quantum states (NQS) are powerful neural-network ansätzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be systematically improvable by increasing the number of parameters. Here we demonstrate an Adaptive scheme to optimize NQSs, through the example of recurrent neural networks (RNN), using a fraction of the computation cost while reducing training fluctuations and impro…

Adaptive Market Intelligence: A Mixture of Experts Framework for Volatility-Sensitive Stock Forecasting
Diego Vallarino
https://arxiv.org/abs/2508.02686 https://

Adaptive Market Intelligence: A Mixture of Experts Framework for Volatility-Sensitive Stock Forecasting
This study develops and empirically validates a Mixture of Experts (MoE) framework for stock price prediction across heterogeneous volatility regimes using real market data. The proposed model combines a Recurrent Neural Network (RNN) optimized for high-volatility stocks with a linear regression model tailored to stable equities. A volatility-aware gating mechanism dynamically weights the contributions of each expert based on asset classification. Using a dataset of 30 publicly traded U.S. stoc…

Multi-Utterance Speech Separation and Association Trained on Short Segments
Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
https://arxiv.org/abs/2507.02562

Multi-Utterance Speech Separation and Association Trained on Short Segments
Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing significantly longer recordings with multiple utterances per speaker than seen during training. In this paper, we investigate how existing approaches perform in this challenging scenario and propose a frequency-temporal recurrent neural network (FTRNN) that effective…

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Ahmad Mustafa, Reza Rastegar, Ghassan AlRegib
https://arxiv.org/abs/2506.19687 …

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Prostate gland segmentation from T2-weighted MRI is a critical yet challenging task in clinical prostate cancer assessment. While deep learning-based methods have significantly advanced automated segmentation, most conventional approaches-particularly 2D convolutional neural networks (CNNs)-fail to leverage inter-slice anatomical continuity, limiting their accuracy and robustness. Fully 3D models offer improved spatial coherence but require large amounts of annotated data, which is often imprac…

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
Luke Rivard, Sun Sun, Hongyu Guo, Wenhu Chen, Yuntian Deng
https://arxiv.org/abs/2507.08800

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
We introduce NeuralOS, a neural framework that simulates graphical user interfaces (GUIs) of operating systems by directly predicting screen frames in response to user inputs such as mouse movements, clicks, and keyboard events. NeuralOS combines a recurrent neural network (RNN), which tracks computer state, with a diffusion-based neural renderer that generates screen images. The model is trained on a large-scale dataset of Ubuntu XFCE recordings, which include both randomly generated interacti…

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
Nicholas H. Barbara, Ruigang Wang, Alexandre Megretski, Ian R. Manchester
https://arxiv.org/abs/2506.01226

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
We study parameterizations of stabilizing nonlinear policies for learning-based control. We propose a structure based on a nonlinear version of the Youla-Kučera parameterization combined with robust neural networks such as the recurrent equilibrium network (REN). The resulting parameterizations are unconstrained, and hence can be searched over with first-order optimization methods, while always ensuring closed-loop stability by construction. We study the combination of (a) nonlinear dynamics, …

Organizational Regularities in Recurrent Neural Networks
Claus Metzner, Achim Schilling, Andreas Maier, Patrick Krauss
https://arxiv.org/abs/2505.22047 htt…

Organizational Regularities in Recurrent Neural Networks
Previous work has shown that the dynamical regime of Recurrent Neural Networks (RNNs) - ranging from oscillatory to chaotic and fixpoint behavior - can be controlled by the global distribution of weights in connection matrices with statistically independent elements. However, it remains unclear how network dynamics respond to organizational regularities in the weight matrix, as often observed in biological neural networks. Here, we investigate three such regularities: (1) monopolar output weigh…

Iola Walker: A Mobile Footfall Detection System for Music Composition
Will James
https://arxiv.org/abs/2506.01211 https://arxiv.org/p…

Iola Walker: A Mobile Footfall Detection System for Music Composition
This project is the first of several experiments composing music that changes in response to biosignals. The system is dubbed "iola walker" in reference to a common polyrhythm, the hemiola. A listener goes for a walk, and the Iola Walker app detects their walking pace. Iola Walker picks up footfalls using a foot-mounted accelerometer, processing the signals in real time using a recurrent neural network in an Android app. The Android app outputs a MIDI event for each footfall. The iola walker pl…

Time Resolution Independent Operator Learning
Diab W. Abueidda, Mbebo Nonna, Panos Pantidis, Mostafa E. Mobasher
https://arxiv.org/abs/2507.02524 https://

Time Resolution Independent Operator Learning
Accurately learning solution operators for time-dependent partial differential equations (PDEs) from sparse and irregular data remains a challenging task. Recurrent DeepONet extensions inherit the discrete-time limitations of sequence-to-sequence (seq2seq) RNN architectures, while neural-ODE surrogates cannot incorporate new inputs after initialization. We introduce NCDE-DeepONet, a continuous-time operator network that embeds a Neural Controlled Differential Equation (NCDE) in the branch and a…

Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
Daniele Ravasio, Marcello Farina, Alessio La Bella, Andrea Ballarino
https://arxiv.org/abs/2506.20334

Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
This paper investigates the design of output-feedback schemes for systems described by a class of recurrent neural networks. We propose a procedure based on linear matrix inequalities for designing an observer and a static state-feedback controller. The algorithm leverages global and regional incremental input-to-state stability (incremental ISS) and enables the tracking of constant setpoints, ensuring robustness to disturbances and state estimation uncertainty. To address the potential limitat…

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
Daniel Szelogowski
https://arxiv.org/abs/2507.21474 https://arxiv.org/pdf/2507…

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
Despite success across diverse tasks, current artificial recurrent network architectures rely primarily on implicit hidden-state memories, limiting their interpretability and ability to model long-range dependencies. In contrast, biological neural systems employ explicit, associative memory traces (i.e., engrams) strengthened through Hebbian synaptic plasticity and activated sparsely during recall. Motivated by these neurobiological insights, we introduce the Engram Neural Network (ENN), a nove…

Replaced article(s) found for cond-mat.quant-gas. https://arxiv.org/list/cond-mat.quant-gas/new
[1/1]:
- Recurrent neural network wave functions for Rydberg atom arrays on kagome lattice
Mohamed Hibat-Allah, Ejaaz Merali, Giacomo Torlai, Roger G Melko, Juan Carrasquilla…

Brain-inspired interpretable reservoir computing with resonant recurrent neural networks
Mark A. Kramer
https://arxiv.org/abs/2506.17083 https://

Brain-inspired interpretable reservoir computing with resonant recurrent neural networks
Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of biological neurons, we describe a reservoir computing framework with explicit damped, oscillatory node dynamics. We express the oscillatory dynamics using two history dependent terms to connect these dynamics with existing artificial neural network approaches an…

Device-Cloud Collaborative Correction for On-Device Recommendation
Tianyu Zhan, Shengyu Zhang, Zheqi Lv, Jieming Zhu, Jiwei Li, Fan Wu, Fei Wu
https://arxiv.org/abs/2506.12687

Device-Cloud Collaborative Correction for On-Device Recommendation
With the rapid development of recommendation models and device computing power, device-based recommendation has become an important research area due to its better real-time performance and privacy protection. Previously, Transformer-based sequential recommendation models have been widely applied in this field because they outperform Recurrent Neural Network (RNN)-based recommendation models in terms of performance. However, as the length of interaction sequences increases, Transformer-based mo…

Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification
Hassan Mortada, Cyril Falcon, Yanis Kahil, Math\'eo Clavaud, Jean-Philippe Michel
https://arxiv.org/abs/2506.11639

Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification
State estimation in stochastic dynamical systems with noisy measurements is a challenge. While the Kalman filter is optimal for linear systems with independent Gaussian white noise, real-world conditions often deviate from these assumptions, prompting the rise of data-driven filtering techniques. This paper introduces Recursive KalmanNet, a Kalman-filter-informed recurrent neural network designed for accurate state estimation with consistent error covariance quantification. Our approach propaga…

Replaced article(s) found for cs.SD. https://arxiv.org/list/cs.SD/new
[1/1]:
- ReMi: A Random Recurrent Neural Network Approach to Music Production
Hugo Chateau-Laurent, Tara Vanhatalo, Wei-Tung Pan, Xavier Hinaut

Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search
Nikolaus Salvatore, Qiong Zhang
https://arxiv.org/abs/2506.17424

Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search
Past work has long recognized the important role of context in guiding how humans search their memory. While context-based memory models can explain many memory phenomena, it remains unclear why humans develop such architectures over possible alternatives in the first place. In this work, we demonstrate that foundational architectures in neural machine translation -- specifically, recurrent neural network (RNN)-based sequence-to-sequence models with attention -- exhibit mechanisms that directly…

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
Siyu Yu, Zihan Qin, Tingshan Liu, Beiya Xu, R. Jacob Vogelstein, Jason Brown, Joshua T. Vogelstein
https://arxiv.org/abs/2507.10951

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures
The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit (BPU), a fixed recurrent network derived directly from synaptic connectivity. Despite its modest size 3,000 neurons and 65,000 weights between them), the unmodified BPU achieves 98% accuracy on MNIST and 58% on CIFAR-10, surpassing size-matched MLPs. Scaling the…