Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

4591136181 · May 202619922001200920172026
48 results for forgetting mechanism

Adaptive model learns from time series data with changing distributions.

problem Predicting time series data under distribution shift.
method Formulates distribution shift as weighted empirical risk minimization. Uses a gradient-based learning method for a forgetting mechanism.
result Proposes an efficient method for adaptive time series prediction.

We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn in…

2019-11-11abs ↗pdf ↗

Dropout helps a stable network learn new tasks without forgetting old ones.

problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Investigate the relationship between dropout and stability in neural networks, showing dropout acts as an implicit gating mechanism.
result Dropout stabilizes a network's learning, allowing it to learn new tasks without forgetting old ones.

Though neural networks have achieved much progress in various applications, it is still highly challenging for them to learn from a continuous stream of tasks without forgetting. Continual learning, a new learning paradigm, aims to solve this issue. In this work, we propose a new model for continual learning, called Ba…

2019-05-10abs ↗pdf ↗

Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserve…

2018-01-04abs ↗pdf ↗

Study analyzes catastrophic forgetting in continual learning using teacher-student networks.

problem Catastrophic forgetting in continuously learning systems.
method Teacher-student learning framework, similarity of input distributions and target functions.
result Network can avoid catastrophic forgetting with small input distribution similarity and large target function similarity.

We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTM…

2017-06-08abs ↗pdf ↗

Paper analyzes stability and forgetting in score-based generative models.

problem Understanding the stability and long-time behavior of generative models.
method Quantitative bounds on sampling error using stability and forgetting properties of the Markov chain.
result Provides practical consequences of stability and contraction mechanism in sampling.

Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.

problem Catastrophic forgetting in streaming generative and predictive learning.
method Unified analysis of stateful replay for autoencoding, forecasting, and classification tasks.
result Stateful replay reduces average forgetting by a factor of 2-3 on heterogeneous multi-task streams.

New interpretation of RNN forget gate improves learnability for long-term sequential data.

problem Improving learnability of recurrent neural networks for long-term temporal dependencies.
method Generalized theory of gated RNNs, focusing on gradient behavior over time.
result Existing RNNs satisfy the gradient condition for initial training, suggesting validity of forget gate interpretation.

Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments. Efforts to combat catastrophic forgetting reported in the literature to date have focused on how control systems can be updated more rapidly, hastening their adjustment from good initial setti…

2019-10-15abs ↗pdf ↗

Bayesian time series forecasting improves by dynamically adapting to recent information.

problem Lack of forgetting mechanism in signature kernel for time series forecasting.
method Introducing a novel forgetting mechanism for signature features using Random Fourier Decayed Signature Features (RFDSF) with Gaussian processes (GPs).
result Demonstrates superior performance compared to other GP-based alternatives and state-of-the-art probabilistic time series forecasting algorithms.

Study on neural networks' performance in sequential task learning.

problem Understanding the performance of neural networks in sequential task learning.
method Theoretical analysis of generalization performance in continual learning using statistical mechanical analysis of kernel ridge-less regression.
result Characteristic transitions from positive to negative transfer observed in neural networks.

A new method helps deep learning systems adapt to changing conditions.

problem Deep learning systems struggle with environmental drifts and long healing cycles.
method Intentional forgetting integrated into continual learning to overcome issues.
result Dr. DRL reduces healing time and fine-tuning episodes by 18.74% and 17.72% respectively.

The creation of machine learning algorithms for intelligent agents capable of continuous, lifelong learning is a critical objective for algorithms being deployed on real-life systems in dynamic environments. Here we present an algorithm inspired by neuromodulatory mechanisms in the human brain that integrates and expan…

2020-01-27abs ↗pdf ↗

D-LinOSS models learn to dissipate energy, improving performance on long-range tasks.

problem Representational limitations of LinOSS models in long-range reasoning.
method Introducing Damped Linear Oscillatory State-Space models (D-LinOSS) that learn to dissipate latent state energy on arbitrary time scales.
result D-LinOSS consistently outperforms previous LinOSS methods on long-range learning tasks, achieving faster convergence and reducing hyperparameter search space.

A neural network learns phase space properties for time series analysis.

problem Lack of consistency and robustness in estimating embedding parameters.
method Forgetting mechanism neural network to learn phase space properties.
result Neural network approach is competitive or superior to state-of-the-art strategies.

Adam optimizer leads to more forgetting in neural networks.

problem Understanding and quantifying catastrophic forgetting in neural networks.
method Comparative analysis of various optimization algorithms and metrics in different learning scenarios.
result Adam optimizer causes more forgetting compared to classical algorithms like SGD.

CUTS removes corruption from models without clean data, improving utility and security.

problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.

This paper investigates how forgetting affects neural network representations and stabilizes deeper layers.

problem Catastrophic forgetting in machine learning models trained on sequential tasks.
method Representational analysis techniques and empirical studies on CIFAR-10 and CIFAR-100 datasets.
result Deeper layers are disproportionately the source of forgetting, and methods to mitigate forgetting stabilize these layers.

The paper proposes selective forgetting for deep neural networks at a finer level than samples.

problem Selective forgetting of deep neural networks to handle outliers, poisoned data, or sensitive information.
method Formulated selective forgetting at a finer level than samples, introduced as an optimization problem on three criteria.
result Experimental results show the model can forget specific information for classification, improving accuracy in specific cases.

New method tackles anomaly detection in video surveillance using continual learning.

problem Challenges in continual learning for high-dimensional applications like video surveillance.
method Transfer learning and continual learning for online anomaly detection.
result Significantly reduces training complexity and continual learning from recent data.

The paper analyzes how forgetting in LLMs is linked to simple task-upstream example associations.

problem Forgetting of upstream knowledge in fine-tuned LLMs.
method Empirical analysis of forgotten examples in NN upstream examples after MM new tasks, using low-rank matrix approximation.
result Forgetting can be predicted efficiently using matrix completion over empirical associations.

Study shows how task similarity affects forgetting in teacher-student setup.

problem Catastrophic forgetting in continual learning.
method Extended teacher-student setup to multiple teachers, analyzing similarity between tasks.
result Task similarity, whether at readouts or features, influences forgetting and transfer.

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade on old tasks when trained successively on new tasks with different data distrib…

2018-11-28abs ↗pdf ↗

Bayesian online meta-learning framework tackles catastrophic forgetting in few-shot classification.

problem Catastrophic forgetting in few-shot classification problems.
method Bayesian online learning, meta-learning, Laplace approximation, variational inference.
result Framework effectively achieves goal of overcoming catastrophic forgetting in few-shot classification.

This work tackles catastrophic forgetting in neural networks by mimicking brain's metaplasticity.

problem Catastrophic forgetting in neural networks, where new tasks erase previously learned ones.
method Interpreting binarized neural networks as metaplastic systems, adjusting their training technique.
result Training technique reduces catastrophic forgetting without needing previously presented data.

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights selection, and progressive networks expansion. By enforcing their integration in an itera…

2019-10-15abs ↗pdf ↗

Study examines how training regime affects neural networks' forgetting.

problem Catastrophic forgetting in neural networks when learning multiple tasks sequentially.
method Analyzes the impact of different training regimes (learning rate, batch size, regularization) on forgetting.
result Training regimes that widen tasks' local minima help prevent catastrophic forgetting.