Neural Information Processing Systems http://nips.cc/

We propose a novel memory cell for recurrent neural networks that dynamically maintains information across long windows of time using relatively few resources. The Legendre Memory Unit (LMU) is mathematically derived to orthogonalize its continuous-time history - doing so by solving d coupled ordinary differential equations (ODEs), whose phase space linearly maps onto sliding windows of time via the Legendre polynomials up to degree d 1. Backpropagation across LMUs outperforms equivalently-sized LSTMs on a chaotic time-series prediction task, improves memory capacity by two orders of magnitude, and significantly reduces training and inference times. LMUs can efficiently handle temporal dependencies spanning 100,000 time-steps, converge rapidly, and use few internal state-variables to learn complex functions spanning long windows of time - exceeding state-of-the-art performance among RNNs on permuted sequential MNIST. These results are due to the network's disposition to learn scale-invariant features independently of step size. Backpropagation through the ODE solver allows each layer to adapt its internal time-step, enabling the network to learn task-relevant time-scales. We demonstrate that LMU memory cells can be implemented using m recurrently-connected Poisson spiking neurons, O(m) time and memory, with error scaling as O(d/ m). We discuss implementations of LMUs on analog and digital neuromorphic hardware.

Deep reinforcement learning (DRL)-based frameworks, featuring Transformer-style policy networks, have demonstrated their efficacy across various vehicle routing problem (VRP) variants. However, the application of these methods to the multi-trip time-dependent vehicle routing problem (MTTDVRP) with maximum working hours constraints -- a pivotal element of urban logistics -- remains largely unexplored. This paper introduces a DRL-based method called the Simultaneous Encoder and Dual Decoder Attention Model (SED2AM), tailored for the MTTDVRP with maximum working hours constraints. The proposed method introduces a temporal locality inductive bias to the encoding module of the policy networks, enabling it to effectively account for the time-dependency in travel distance or time. The decoding module of SED2AM includes a vehicle selection decoder that selects a vehicle from the fleet, effectively associating trips with vehicles for functional multi-trip routing. Additionally, this decoding module is equipped with a trip construction decoder leveraged for constructing trips for the vehicles. This policy model is equipped with two classes of state representations, fleet state and routing state, providing the information needed for effective route construction in the presence of maximum working hours constraints. Experimental results using real-world datasets from two major Canadian cities not only show that SED2AM outperforms the current state-of-the-art DRL-based and metaheuristic-based baselines but also demonstrate its generalizability to solve larger-scale problems.

In continual time series analysis using neural networks, catastrophic forgetting (CF) of previously learned models when training on new data domains has always been a significant challenge. This problem is especially challenging in vehicle estimation and control, where new information is sequentially introduced to the model. Unfortunately, existing work on continual learning has not sufficiently addressed the adverse effects of catastrophic forgetting in time series analysis, particularly in multivariate output environments. In this paper, we present EM-ReSeleCT (Efficient Multivariate Representative Selection for Continual Learning in Time Series Tasks), an enhanced approach designed to handle continual learning in multivariate environments. Our approach strategically selects representative subsets from old and historical data and incorporates memory-based continual learning techniques with an improved optimization algorithm to adapt the pre-trained model on new information while preserving previously acquired information. Additionally, we develop a sequence-to-sequence transformer model (autoregressive model) specifically designed for vehicle state estimation. Moreover, we propose an uncertainty quantification framework using conformal prediction to assess the sensitivity of the memory size and to showcase the robustness of the proposed method. Experimental results from tests on an electric Equinox vehicle highlight the superiority of our method in continually learning new information while retaining prior knowledge, outperforming state-of-the-art continual learning methods. Furthermore, EM-ReSeleCT significantly reduces training time, a critical advantage in continual learning applications.

Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit regularization to enforce a globally structured latent space. This limitation often leads to suboptimal generalization. We propose SinSim, a novel extension of SimCLR that integrates Sinkhorn regularization from optimal transport theory to enhance representation structure. The Sinkhorn loss, an entropy-regularized Wasserstein distance, encourages a well-dispersed and geometry-aware feature space, preserving discriminative power. Empirical evaluations on various datasets demonstrate that SinSim outperforms SimCLR and achieves competitive performance against prominent self-supervised methods such as VICReg and Barlow Twins. UMAP visualizations further reveal improved class separability and structured feature distributions. These results indicate that integrating optimal transport regularization into contrastive learning provides a principled and effective mechanism for learning robust, well-structured representations. Our findings open new directions for applying transport-based constraints in self-supervised learning frameworks.

Machine learning developers frequently use interactive computational notebooks, such as Jupyter notebooks, to host code for data processing and model training. Jupyter notebooks provide a convenient tool for writing machine learning pipelines and interactively observing outputs, however, maintaining Jupyter notebooks, e.g., to add new features or fix bugs, can be challenging due to the length and complexity of the notebooks. Moreover, there is no existing benchmark related to developer edits on Jupyter notebooks. To address this, we present the first dataset of 48,398 Jupyter notebook edits derived from 20,095 revisions of 792 machine learning repositories on GitHub, and perform the first study of the using LLMs to predict code edits in Jupyter notebooks. Our dataset captures granular details of cell-level and line-level modifications, offering a foundation for understanding real-world maintenance patterns in machine learning workflows. We observed that the edits on Jupyter notebooks are highly localized, with changes averaging only 166 lines of code in repositories. While larger models outperform smaller counterparts in code editing, all models have low accuracy on our dataset even after finetuning, demonstrating the complexity of real-world machine learning maintenance tasks. Our findings emphasize the critical role of contextual information in improving model performance and point toward promising avenues for advancing large language models' capabilities in engineering machine learning code.

Depression has impacted millions of people worldwide and has become one of the most prevalent mental disorders. Early mental disorder detection can lead to cost savings for public health agencies and avoid the onset of other major comorbidities. Additionally, the shortage of specialized personnel is a critical issue because clinical depression diagnosis is highly dependent on expert professionals and is time consuming. In this study, we explore the use of GPT-4 for clinical depression assessment based on transcript analysis. We examine the model's ability to classify patient interviews into binary categories: depressed and not depressed. A comparative analysis is conducted considering prompt complexity (e.g., using both simple and complex prompts) as well as varied temperature settings to assess the impact of prompt complexity and randomness on the model's performance. Results indicate that GPT-4 exhibits considerable variability in accuracy and F1-Score across configurations, with optimal performance observed at lower temperature values (0.0-0.2) for complex prompts. However, beyond a certain threshold (temperature >= 0.3), the relationship between randomness and performance becomes unpredictable, diminishing the gains from prompt complexity. These findings suggest that, while GPT-4 shows promise for clinical assessment, the configuration of the prompts and model parameters requires careful calibration to ensure consistent results. This preliminary study contributes to understanding the dynamics between prompt engineering and large language models, offering insights for future development of AI-powered tools in clinical settings.

This study evaluates fine-tuning strategies for text classification using the DistilBERT model, specifically the distilbert-base-uncased-finetuned-sst-2-english variant. Through structured experiments, we examine the influence of hyperparameters such as learning rate, batch size, and epochs on accuracy, F1-score, and loss. Polynomial regression analyses capture foundational and incremental impacts of these hyperparameters, focusing on fine-tuning adjustments relative to a baseline model. Results reveal variability in metrics due to hyperparameter configurations, showing trade-offs among performance metrics. For example, a higher learning rate reduces loss in relative analysis (p=0.027) but challenges accuracy improvements. Meanwhile, batch size significantly impacts accuracy and F1-score in absolute regression (p=0.028 and p=0.005) but has limited influence on loss optimization (p=0.170). The interaction between epochs and batch size maximizes F1-score (p=0.001), underscoring the importance of hyperparameter interplay. These findings highlight the need for fine-tuning strategies addressing non-linear hyperparameter interactions to balance performance across metrics. Such variability and metric trade-offs are relevant for tasks beyond text classification, including NLP and computer vision. This analysis informs fine-tuning strategies for large language models and promotes adaptive designs for broader model applicability.

With the approach of the High Luminosity Large Hadron Collider (HL-LHC) era set to begin particle collisions by the end of this decade, it is evident that the computational demands of traditional collision simulation methods are becoming increasingly unsustainable. Existing approaches, which rely heavily on first-principles Monte Carlo simulations for modeling event showers in calorimeters, are projected to require millions of CPU-years annually -- far exceeding current computational capacities. This bottleneck presents an exciting opportunity for advancements in computational physics by integrating deep generative models with quantum simulations. We propose a quantum-assisted hierarchical deep generative surrogate founded on a variational autoencoder (VAE) in combination with an energy conditioned restricted Boltzmann machine (RBM) embedded in the model's latent space as a prior. By mapping the topology of D-Wave's Zephyr quantum annealer (QA) into the nodes and couplings of a 4-partite RBM, we leverage quantum simulation to accelerate our shower generation times significantly. To evaluate our framework, we use Dataset 2 of the CaloChallenge 2022. Through the integration of classical computation and quantum simulation, this hybrid framework paves way for utilizing large-scale quantum simulations as priors in deep generative models.