Deep-IRT combines deep learning and IRT for explainable knowledge tracing.
problem Lack of explainability in deep learning-based knowledge tracing models.
method Synthesis of DKVMN and IRT models to estimate student and item parameters.
result Deep-IRT retains DKVMN performance while providing psychological interpretations.
Paper extends knowledge tracing algorithms to infer student knowledge and predict posttest performance.
problem Lack of algorithms that directly infer student knowledge and predict posttest performance.
method Extended DKT and DKVMN to infer knowledge, and applied to BKT and PFA for comparison.
result Knowledge estimates from the extended algorithms correlate better with posttest performance than existing methods.
SKVMN improves KT models by tracing student knowledge states and dependencies.
problem Tackling limitations of existing KT models in deep learning.
method Proposes SKVMN, a deep learning model unifying recurrent and memory capacities.
result Significantly outperforms state-of-the-art KT models on multiple datasets.
SAKT improves knowledge tracing by focusing on relevant past activities.
problem Handling sparse data in knowledge tracing models.
method Self-attention based approach to identify relevant past activities.
result SAKT outperforms state-of-the-art models, improving AUC by 4.43%.
FF layers in transformers are nearly as interpretable as sparse autoencoders.
problem Comparing interpretability of feature vectors in FF layers vs. sparse autoencoders.
method Revisited interpretability of FF layers as key-value memories using modern benchmarks.
result FF and SAE feature vectors are similarly interpretable, but FFs can be better in some aspects.
Service-induced congestion in memory-constrained LLM serving
problem Service-induced congestion in memory-constrained large language model (LLM) serving
method Developing a discrete-time dynamical model of memory-constrained LLM inference
result The system converges to a unique worst-case limit cycle that is asymptotically stable outside a Lebesgue-measure-zero exact-capture set, with throughput losses as large as 50%.
Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable…
Improved stock price prediction using attention modules and news sentiment.
problem Predicting stock prices with non-stationary and non-parametric data.
method α_{t}-RIM architecture with attention modules and exponentially smoothed recurrent neural network.
result The αt-RIM outperforms state-of-the-art models in predicting unseen data. OSA overcomes instability in skipless Transformers.
problem Instability in skipless Transformers using Softmax Self-Attention.
method OSA parametrizes attention matrix to be orthogonal via skew-symmetric matrix exponential.
result OSA allows for training non-causal Transformers without skip connections and normalisation layers.
New algorithm reduces costs and latency for large language model inference.
problem Optimizing inference costs and latency for large language models with GPU constraints.
method Formulated as an online scheduling problem with endogenous memory growth, introduced fluid model and WAIT algorithms.
result Reduced costs and latency, especially in near-overloaded and overloaded regimes.
Generative diffusion models mimic biological memory networks, encoding associative dynamics in deep neural weights.
problem Understanding long-term memory mechanisms in neuroscience and AI.
method Interpreting generative diffusion models as energy-based models and comparing them to Hopfield networks.
result Generative diffusion models can encode associative dynamics of Hopfield networks in deep neural weights.
NeuZip compresses neural network weights to save memory during training and inference.
problem Memory constraints in neural network training and inference.
method Entropy-based dynamic weight compression.
result Significant reduction in memory usage without performance loss.
Improves memory robustness in RNNs for sequential data.
problem Improving memory robustness in RNNs for sequential data processing.
method Utilized various training protocols, datasets, and architectures to analyze hidden state dynamics and propose a regularization technique.
result Manipulating hidden state speeds improves memory robustness over time.
Meta-learning approach for fast and compressive energy-based memory models.
problem Learning associative memory with fast and compressive models for complex data.
method Meta-learning approach to energy-based memory models (EBMM) using arbitrary neural architectures.
result Demonstrated associative retrieval outperforming existing systems in reconstruction error and compression rate.
Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an emphasis on biological plausibility of memory dynamics and learning. We find that …
NEST optimizes deep learning training by placing devices efficiently across networks and memory.
problem Inefficient device placement in distributed deep learning leads to high communication and memory overhead.
method NEST uses network-, compute-, and memory-aware dynamic programming to optimize device placement.
result NEST achieves up to 2.43 times higher throughput and better memory efficiency.
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
problem Order of nodes in irregular neural networks affects memory footprint, complicating execution under resource constraints.
method Memory-aware compiler using dynamic programming and graph rewriting to find optimal schedules.
result Achieves optimal peak memory and further improves it with graph rewriting, reducing memory usage by 1.68x-1.86x compared to TensorFlow Lite.
Deep neural networks with memory learn reduced equations from partial data.
problem Constructing governing equations for unknown dynamical systems from limited data.
method Formulate a discrete approximation of memory integrals, use deep neural networks to incorporate history terms.
result Deep neural networks can learn reduced equations with memory from partial data.
Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune it with new data. Here, we show that, surprisingly, this is indeed possible. The …
A new method reduces memory usage in neural networks by 36-81%.
problem Minimizing memory usage in neural networks during backpropagation.
method Formalized as a graph theory problem, uses dynamic programming to minimize computational overhead.
result Reduces peak memory consumption by 36-81% on various networks.
Study on memory effects in RNNs learning temporal data.
problem Understanding memory effects in RNNs for temporal data learning.
method Mathematical analysis of continuous-time linear RNNs, focusing on approximation and optimization dynamics.
result Long-term memory requires a large number of neurons and slows down training.
Linear memory stores associations up to a logarithmic scale, but listwise retrieval can handle a quadratic scale.
problem How many key-value associations can a linear memory store?
method Analyzed linear memory models for top-1 and listwise retrieval, proving phase transitions and developing asymptotic theories.
result Linear memory has a logarithmic capacity for top-1 retrieval and a quadratic capacity for listwise retrieval.
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked …
This paper introduces a hierarchical associative memory model with multiple layers.
problem Limitations of traditional associative memory models with only one hidden layer.
method Develops a fully recurrent model with arbitrary layers, including locally connected ones, and a corresponding energy function.
result The model can dynamically assemble memories using weights from lower layers and higher layers' rules.
Improved recurrent neural networks learn long-term dependencies through multi-scale memory.
problem Capturing long-term dependencies in recurrent neural networks.
method Incremental training of a modular RNN architecture with multi-scale hidden states.
result Incremental training and multi-scale memory enhance RNNs' ability to learn long-term dependencies.
DCRNN improves LSTM for chaotic dynamical system forecasting.
problem Modeling chaotic dynamical systems with recurrent neural networks.
method DCRNN incorporates learnable skip-connections and a Lyapunov stability regularization term.
result DCRNN outperforms LSTM in 100 out of 100 experiments, reducing mean squared error by 80.0%.
A central challenge faced by memory systems is the robust retrieval of a stored pattern in the presence of interference due to other stored patterns and noise. A theoretically well-founded solution to robust retrieval is given by attractor dynamics, which iteratively clean up patterns during recall. However, incorporat…
New model captures long-term memory effects in epidemic dynamics.
problem Identifying memory effects in disease progression and recovery.
method Physics-informed neural networks (PINN) with fractional SEIRD model.
result Fractional memory order α improves predictive performance over classical models. New method combines long-memory reservoirs for accurate dengue forecasting from short data.
problem Accurate dengue forecasting from short, noisy, non-stationary, and nonlinear data.
method Fractional ESN and Wavelet ESN frameworks integrating long-term memory.
result fESN and wESN outperform baselines in multiple dengue datasets and forecasting horizons.
Enhances option pricing with fractional order Black-Scholes-Merton model.
problem Improving precision and authenticity of option pricing.
method Integrates fractional order Black-Scholes-Merton with neural networks.
result Improves accuracy in capturing complex diffusion dynamics and memory effects.
New neural operators model turbulence with memory and randomness.
problem Modeling turbulence in complex fluid dynamics with memory and randomness.
method Symmetrized activation functions, fractional derivatives, and stochastic noise.
result Theoretical guarantees for approximation quality in turbulent phenomena.
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in t…
Neural ARFIMA model improves exchange rate forecasting for BRIC economies.
problem Forecasting exchange rates for emerging markets with long-term memory and nonlinear dynamics.
method Integrates ARFIMA for long-memory with neural networks for nonlinear approximation.
result NARFIMA model outperforms benchmarks in BRIC exchange rate forecasting.
Develops LSTM for predicting neuronal dynamics over long time-horizons.
problem Understanding and controlling complex brain behaviors.
method Long Short-Term Memory (LSTM) neural network architecture for multi-time step predictions.
result LSTM improves short time-horizon prediction accuracy and multi-time step predictions of neuronal dynamics.
Researchers develop a neural network that learns like humans, overcoming forgetting and structure issues.
problem Catastrophic forgetting and structure limitations in neural networks.
method Memory playback strategy and dynamic structure extension using conditional variational autoencoder (CVAE).
result The method effectively prevents forgetting and allows for dynamic network growth.
We study the inference of a model of dynamic networks in which both communities and links keep memory of previous network states. By considering maximum likelihood inference from single snapshot observations of the network, we show that link persistence makes the inference of communities harder, decreasing the detectab…
A new theory explains large associative memory with biological plausibility.
problem Large associative memory in neurobiology and machine learning.
method Microscopic theory with hidden neurons and two-body interactions.
result Valid model of large associative memory with biological plausibility.
A new algorithm reduces memory usage for deep learning models.
problem Training deep learning models requires significant memory.
method Dynamic Tensor Rematerialization (DTR) is a greedy online algorithm that dynamically plans recomputations.
result DTR achieves comparable performance to optimal static checkpointing with only a small memory budget.
Develops hyperparameter transfer methods for Dense Associative Memories.
problem Challenges in transferring hyperparameters for DenseAMs due to unique architecture and activation functions.
method Derives explicit prescriptions for hyperparameter transfer from small to large models.
result Excellent agreement between theoretical and empirical results.
When analyzing the genome, researchers have discovered that proteins bind to DNA based on certain patterns of the DNA sequence known as "motifs". However, it is difficult to manually construct motifs due to their complexity. Recently, externally learned memory models have proven to be effective methods for reasoning ov…
New cooperative dynamics enhances retrieval performance in neural networks.
problem Understanding emergent computational capabilities in disordered systems.
method Leveraging statistical mechanics, extended neural network architecture for hetero-associative memory.
result Layers trained with less informative datasets develop retrieval regions of the same amplitude, leading to optimal performance.
V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
Proposes a plastic neural memory model for better anomaly detection.
problem Static attention mechanisms limit NMNs in anomaly detection.
method Introduces dynamic connection weights for improved knowledge retrieval.
result Outperforms state-of-the-art in three medical anomaly detection tasks.
Study on neural networks with non-normal interactions reveals unique spectral properties.
problem Understanding episodic memory encoding in the brain.
method Developed a neural network model with non-Hermitian couplings and applied random matrix theory.
result Spectral density of the model is non-uniform and can transition to chaos, providing computational benefits.
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzm…
Paper uses deep reinforcement learning for network slicing and traffic prediction.
problem Managing dynamic network slices while maintaining QoS in a 5G environment.
method Integrates LSTM for traffic prediction and DDRL for distributed decision-making.
result Significant improvements in network performance, reducing QoS violations.
TGNs learn from dynamic graphs efficiently and outperform previous methods.
problem Learning from graphs that evolve over time.
method Temporal Graph Networks (TGNs) combining memory and graph operators.
result Significantly outperforms previous approaches on dynamic graphs.
Comprehending complex systems by simplifying and highlighting important dynamical patterns requires modeling and mapping higher-order network flows. However, complex systems come in many forms and demand a range of representations, including memory and multilayer networks, which in turn call for versatile community-det…