Intrinsic fear prevents catastrophic states in reinforcement learning.
problem Catastrophic forgetting in reinforcement learning.
method Intrinsic fear (IF) is a learned reward shaping that penalizes the Q-learning objective based on the probability of imminent catastrophe.
result Intrinsic fear models prevent periodic catastrophes in reinforcement learning agents.
Proposes a method to prevent neural networks from forgetting learned tasks.
problem Catastrophic forgetting in neural networks.
method Attention-based selective plasticity of synapses inspired by the cholinergic neuromodulatory system.
result Competitive performance on benchmark tasks compared to state-of-the-art methods.
New method prevents forgetting in continual learning tasks.
problem Catastrophic forgetting in continual learning.
method Generative regularization integrated into Bayesian inference framework.
result Empirically outperforms state-of-the-art methods on various datasets.
Continual state learning model using generative replay for RL.
problem Efficiently learn and adapt state representations as the environment changes.
method Variational Auto-Encoders for state representation and Generative Replay for past knowledge.
result Automatic environment change detection and efficient state representation.
AI learns to learn sequentially without forgetting.
problem Preventing catastrophic forgetting in machine learning models.
method Meta-learning a neuromodulatory activation-gating function to control selective activation in deep neural networks.
result State-of-the-art continual learning performance with 600 classes (9,000 updates).
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.
CLAW adapts weights to balance continual learning and catastrophic forgetting.
problem Balancing continual learning across multiple tasks without forgetting previous knowledge.
method Probabilistic modelling and variational inference to adaptively share network components.
result CLAW achieves state-of-the-art performance in continual learning benchmarks.
SupportNet tackles catastrophic forgetting in incremental learning with support data.
problem Catastrophic forgetting in deep learning models when learning new data.
method SupportNet combines deep learning and SVM to identify support data, which are used to reinforce old data knowledge.
result SupportNet outperforms state-of-the-art methods and matches deep learning models trained from scratch on both old and new data.
SeNA-CNN prevents forgetting in CNNs by selectively augmenting networks.
problem Preventing catastrophic forgetting in neural networks.
method Selective network augmentation to learn new tasks without forgetting old ones.
result SeNA-CNN outperforms state-of-the-art Learning without Forgetting algorithms in some scenarios.
The study examines insurance demand under rough volatility and path-dependent shocks.
problem Optimal insurance and investment strategies under rough volatility and path-dependent shocks.
method Rough volatility model and Hawkes process with power kernel, Functional Ito formula extension.
result Individuals demand more catastrophe insurance when path-dependent effects are considered.
Dynamic information balancing reduces catastrophic forgetting in modular neural networks.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.
Paper tackles forgetting in neural networks, proposing solutions.
problem Catastrophic forgetting in artificial neural networks.
method Simple model and reinforcement learning applications.
result Proposes solutions to prevent forgetting in neural networks.
The paper tackles safe exploration in RL by a conservative safety critic.
problem Safe exploration in reinforcement learning (RL) when partially trained policies are deployed.
method Learning a conservative safety estimate through a critic, provably bounding catastrophic failures.
result The approach provably converges to competitive task performance with significantly lower catastrophic failure rates.
Clusters of financial market states identified over 2006-2019.
problem Understanding the statistical properties of financial markets.
method Clustering analysis of correlation matrices constructed from sliding epochs.
result Financial markets can be classified into distinct states with transitions indicating precursors to catastrophic events.
S-TRIGGER learns state representations for continual learning.
problem Efficiently compress and maintain past knowledge in changing environments.
method Generative Replay with self-triggered environment change detection.
result S-TRIGGER enables fast and high-performing Reinforcement Learning without catastrophic forgetting.
New method uses dynamic programming for meta continual learning.
problem Challenges of generalization and catastrophic forgetting in sequential learning.
method Developed a theoretical framework using dynamic programming for meta continual learning.
result Theoretical and practical method achieves better accuracy than existing methods.
VCL combines online VI and Monte Carlo VI for neural networks.
problem Catastrophic forgetting in continual learning.
method Fuses online variational inference and Monte Carlo VI.
result VCL outperforms state-of-the-art methods on various tasks.
The study values a new type of insurance-linked security called CocoCat bonds.
problem Valuing a new type of insurance-linked security called contingent convertible catastrophe bonds.
method Formalized design, derived analytical valuation formulae, used time-inhomogeneous compound Poisson process for natural catastrophe losses, and applied exponential change of measure and Girsanov-like transformation.
result CocoCat bond prices are most sensitive to interest rates, conversion fractions, and trigger levels.
A neural network approach to learn Cusp Catastrophe dynamics.
problem Complex behavior and non-convex parameter space in Cusp Catastrophe models.
method Training a deep neural network to learn dynamics without solving generating parameters.
result Demonstrated a neural network approach for the first time in Cusp Catastrophe models.
New method tackles catastrophic forgetting and order-sensitivity in continual learning.
problem Catastrophic forgetting and order-sensitivity in continual learning.
method Additive Parameter Decomposition (APD) to represent task parameters as a sum of shared and adaptive parts.
result Significantly outperforms state-of-the-art methods in accuracy, scalability, and order-robustness.
The paper values reinsurance contracts for dynamic catastrophe claims without arbitrage.
problem Valuation of reinsurance contracts for dynamic catastrophe claims without arbitrage.
method Compound dynamic contagion process, Esscher transform, Monte Carlo simulation.
result Arbitrage-free premiums for catastrophe stop-loss reinsurance contracts.
Overparameterized models improve performance in sequential learning tasks.
problem Catastrophic forgetting in overparameterized neural networks.
method Two-task linear regression problem with random orthogonal transformations.
result Overparameterization mitigates catastrophic forgetting in sequential learning tasks.
Random forest predicts catastrophe bond spreads with 93% accuracy.
problem Predicting spreads in the primary catastrophe bond market.
method Random forest approach using all information in offering circulars.
result Random forest explains 93% of spread variability, significantly better than linear regression (47%).
New framework SEU solves lifelong learning's catastrophic forgetting issue.
problem Catastrophic forgetting in lifelong learning.
method Introduces Neural Architecture Search into lifelong learning to dynamically adapt model structures for different tasks.
result Achieves higher accuracy with significantly smaller model size (25-33% of state-of-the-art methods).
Study on how task sequence properties affect continual learning algorithms.
problem Understanding how task sequence properties influence continual learning algorithms.
method Proposes a new procedure using task space modeling and correlation analysis.
result Error rates are correlated to a task sequence's total complexity but not to sequential heterogeneity.
Autoencoder reduces memory overhead in incremental class learning.
problem Catastrophic forgetting in continual learning.
method Uses autoencoder to extract prototypes and store mean prototypes per class.
result Comparable performance to state-of-the-art with lower memory cost.
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.
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.
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
problem Catastrophic forgetting and memory limitations in continual learning.
method Trains autoencoders with Neural Style Transfer to encode images, replay encoded episodes to avoid forgetting, and use centroids and covariance matrices for pseudo-images when memory is full.
result Increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.
Unified Bayesian framework for CAT bond pricing.
problem Uncertainty in catastrophe occurrences and interest rates in CAT bond markets.
method Bayesian framework based on uncertainty quantification of catastrophes and interest rates.
result Unified asset pricing approach with informative expected risk premia.
Paper introduces Auto DeepVis to explain catastrophic forgetting in continual learning.
problem Catastrophic forgetting in continual learning of deep neural networks.
method Auto DeepVis and critical freezing techniques to address catastrophic forgetting.
result Critical freezing outperforms other methods on both past and future tasks.
Trust is a collective, self-fulfilling phenomenon that suggests analogies with phase transitions. We introduce a stylized model for the build-up and collapse of trust in networks, which generically displays a first order transition. The basic assumption of our model is that whereas trust begets trust, panic also begets…
Paper benchmarks CF mitigation in federated time series forecasting.
problem Catastrophic forgetting in federated learning for time series forecasting.
method Comprehensive evaluation of CF mitigation strategies in federated time series forecasting.
result Introduction of a new benchmark for CF in time series federated learning.
New method uses unlabeled data to prevent forgetting in deep learning.
problem Catastrophic forgetting in lifelong learning with deep neural networks.
method Class-incremental learning scheme with global distillation, confidence-based sampling, and learning strategy.
result Significantly higher accuracy and less forgetting compared to state-of-the-art methods.
Optimizes diversification in catastrophe risk pooling using asymptotic analysis.
problem Maximizing diversification benefit from catastrophic events in insurance pools.
method Asymptotic analysis to solve high-dimensional optimization problem.
result Derives an asymptotically optimal pool that approximates practical optimal pool.
Paper tackles catastrophic forgetting in neural networks with an adversarial feature alignment method.
problem Dramatic performance degradation when new tasks are added to an existing neural network model.
method Inspired by human learning, the paper proposes an adversarial feature alignment method to decompose complex tasks into easier goals.
result The proposed method outperforms state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks.
Study helps identify which ANN parameters cause forgetting.
problem Catastrophic forgetting in neural networks.
method Determines individual parameter contributions to forgetting.
result Identifies specific ANN parameters causing forgetting.
Paper proposes CNE-net to tackle incremental learning in (T)ACSA tasks.
problem Catastrophic forgetting in multi-task incremental learning for (T)ACSA.
method Category Name Embedding network (CNE-net) with shared encoder and decoder.
result State-of-the-art performance on (T)ACSA benchmark datasets.
SALeRA controls SGD learning rate to learn as fast as possible but not faster.
problem Catastrophic learning episodes in SGD training of deep neural networks.
method SALeRA uses two statistical tests: one for speeding up and one for detecting and halting catastrophic episodes.
result SALeRA learns as fast as possible but not faster, as demonstrated by experiments on standard benchmarks.
CBLN uses Bayesian Neural Networks to prevent forgetting in continual learning.
problem Catastrophic forgetting in neural networks when learning new tasks.
method CBLN uses Bayesian Neural Networks to allocate resources to new tasks without forgetting old knowledge.
result CBLN effectively addresses catastrophic forgetting in continual learning.
A new method approximates loss functions asymmetrically to prevent catastrophic forgetting.
problem Catastrophic forgetting in deep neural networks.
method Approximating a true loss function using an asymmetric quadratic function with one side overestimated.
result Achieves state-of-the-art accuracy close to upper-bound performance on benchmark datasets.
Paper tackles catastrophic overfitting in single-step adversarial training.
problem Catastrophic overfitting leads to sudden drop in robust accuracy.
method Proposes a method to prevent overfitting by using all adversarial examples.
result Demonstrates prevention of catastrophic overfitting and improves robustness.
Solves catastrophic forgetting in deep neural networks by generating task-relevant items.
problem Catastrophic forgetting in sequential learning of neural networks.
method Used a Generative Adversarial Network to generate items for rehearsing previous tasks.
result Deep network retains 1.67% absolute accuracy on CIFAR-10 and gains 0.24% on SVHN after learning multiple tasks.
New methods improve insurance data quality for catastrophic events.
problem Improving precision and size of insurance data for catastrophic events.
method Bootstrap, bootknife, and GAN algorithms.
result Compared MSE and MAE of simulated outputs, direct algorithm for fuzzy expert opinion.
SketchOGD improves memory efficiency for continual learning.
problem Catastrophic forgetting in continual learning.
method Matrix sketching to compress model gradients.
result SketchOGD outperforms existing memory-efficient OGD variants.
This paper develops a two-step estimation methodology, which allows us to apply catastrophe theory to stock market returns with time-varying volatility and model stock market crashes. Utilizing high frequency data, we estimate the daily realized volatility from the returns in the first step and use stochastic cusp cata…
New model prevents forgetting in continual learning.
problem Learning from a continuous stream of tasks without forgetting.
method Bayesian Optimized Continual Learning with Attention Mechanism (BOCL).
result BOCL outperforms state-of-the-art in preventing catastrophic forgetting and fitting new tasks better.
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.