Co-adaptive learning helps unknown algorithms perform tasks better than fixed decoders.
problem Improving unknown algorithms' performance in closed-loop settings.
method Proves co-adaptive learning outperforms fixed decoders under certain conditions.
result Co-adaptive learning guarantees better performance than fixed decoders.
Paper proposes efficient co-adaptation of robot morphology and behavior.
problem Infeasibility of co-adapting morphology and behavior in robots due to long manufacturing times and need for new controllers.
method Uses deep reinforcement learning, specifically the soft actor critic algorithm, to automatically and efficiently co-adapt robot morphology and behavior.
result Reduces the number of morphologies and behaviors tested, making co-adaptation more data-efficient.
FOCA method prevents co-adaptation between feature extractor and classifier.
problem Co-adaptation between feature extractor and classifier degrades neural network performance.
method FOCA method uses randomly-generated, weak classifiers to optimize feature extractor without explicit co-adaptation.
result FOCA features form a point-like distribution within the same class under special conditions.
Continuous dropout mimics brain neuron firing rates to prevent feature detector co-adaptation.
problem Preventing overfitting in deep neural networks.
method Extending binary dropout to continuous dropout, inspired by brain neuron firing rates.
result Continuous dropout improves test performance by preventing feature detector co-adaptation.
Dropout improves neural networks by accelerating gradient flow.
problem Understanding why dropout works and improving neural network performance.
method Proposed an optimization technique to push input towards saturation area of activation functions.
result Gradient acceleration in activation function (GAAF) improves image classification performance.
RotationOut rotates input vectors to regularize neural networks.
problem Reduction of co-adaptation in neural networks.
method Randomly rotates input vectors of the input layer.
result RotationOut reduces co-adaptation better than Dropout.
CODA resolves coordination issues in offline multi-agent reinforcement learning.
problem Coordination failure in offline multi-agent reinforcement learning.
method Diffusion-based multi-agent trajectory generator for data augmentation.
result CODA resolves coordination pathologies in continuous polynomial games and complex benchmarks.
Dropout has recently emerged as a powerful and simple method for training neural networks preventing co-adaptation by stochastically omitting neurons. Dropout is currently not grounded in explicit modelling assumptions which so far has precluded its adoption in Bayesian modelling. Using Bayesian entropic reasoning we s…
Researchers analyze how algorithmic and implementation choices affect RL performance.
problem Difficulty in separating algorithmic and implementation differences in RL performance.
method Unified derivations through a single control-as-inference objective, categorizing algorithms as EM or KL minimization.
result Implementation details are co-adapted with algorithmic choices, some transferable across algorithms.
Tabu Dropout improves performance of standard Dropout by generating more diverse neural network architectures.
problem Preventing co-adaptation of neurons in deep neural networks.
method Integrates a diversification strategy into dropout, marking units from the last forward propagation for re-selection in the current forward propagation.
result Improves performance of standard Dropout on MNIST and Fashion-MNIST datasets.
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
Hessian-free (HF) optimization has been successfully used for training deep autoencoders and recurrent networks. HF uses the conjugate gradient algorithm to construct update directions through curvature-vector products that can be computed on the same order of time as gradients. In this paper we exploit this property a…
Develops non-Markovian couplings for sub-Riemannian Brownian motions.
problem Constructing couplings for sub-Riemannian Brownian motions starting from points on the same vertical fiber.
method Uses global isometries to construct maximal couplings, satisfying a reflection principle.
result Estimates coupling time and applies to inequalities for the heat semigroup.
Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which w…
Dropout and RaM become equivalent in large ResNets as depth and width increase.
problem Improving performance in deep learning models.
method Comparing Dropout and Random Gradient Masking in ResNets.
result Dropout and RaM converge to the same large-scale limiting dynamics in ResNets.
We analyze dropout in deep networks with rectified linear units and the quadratic loss. Our results expose surprising differences between the behavior of dropout and more traditional regularizers like weight decay. For example, on some simple data sets dropout training produces negative weights even though the output i…
Curriculum Dropout improves neural network training by gradually increasing difficulty.
problem Overfitting and suboptimal performance during training.
method Adaptive dropout probability scheduling.
result Curriculum Dropout leads to better generalization and performance.
AON improves neural network generalization by making weights approximately orthogonal.
problem Improving generalization of deep neural networks.
method Approximated orthonormal normalisation (AON) technique to make weight vectors approximately orthogonal.
result AON yields promising validation performance compared to orthonormal regularisation.
Proposes a new method to prevent overfitting in deep neural networks.
problem Overfitting in deep neural networks with many trainable parameters.
method Randomly replaces elements in feature maps with specific values during training.
result Improves the testing performance of deep neural networks on benchmark datasets.
Dropout is explained as a structured shrinkage prior in neural networks.
problem Understanding the effectiveness of dropout in preventing overfitting.
method Proposes a novel framework to explain dropout as a structured shrinkage prior, considering continuous distributions and Bernoulli noise.
result Dropout's Monte Carlo training objective approximates marginal MAP estimation.
SDQL uses modular deep Q networks to efficiently learn multi-stage optimal control tasks.
problem Training complex deep reinforcement learning models for multi-stage control tasks is inefficient and unstable.
method Stacked Deep Q Learning (SDQL) with modular Q networks and backward training.
result SDQL efficiently learns optimal control policies for multi-stage tasks with high-dimensional state and action spaces.
Regularized recurrent attention filter combines sensor inputs.
problem Combining information from different sensor modalities.
method Regularized recurrent attention filter, co-learning mechanism, probabilistic graphical model.
result Dynamic sensor fusion and latent representation recovery.
Loyal buyer-seller relationships can arise by design, e.g. when a seller tailors a product to a specific market niche to accomplish the best possible returns, and buyers respond to the dedicated efforts the seller makes to meet their needs. We ask whether it is possible, instead, for loyalty to arise spontaneously, and…
Enhances DenseNets with multi-scale convolutions and stochastic feature reuse.
problem Overfitting in DenseNets with dense feature reuse.
method Multi-scale Convolution Aggregation module and Stochastic Feature Reuse.
result Significant improvement in model accuracy with fewer parameters.
New method uses randomized sparse neural networks to solve time-dependent PDEs more accurately and efficiently.
problem Numerical challenges in training neural networks sequentially in time to solve time-dependent PDEs.
method Introduces Neural Galerkin schemes that update randomized sparse subsets of network parameters at each time step.
result Up to two orders of magnitude more accurate and two orders of magnitude faster than dense update schemes.
Model shows how multiple markets can coexist or fragment based on trader behavior.
problem Understanding market competition and coexistence among multiple trading venues.
method Stylized model of traders making repeated decisions at three markets, analyzed numerically and analytically.
result Parameters like memory length and choice intensity determine whether markets coexist or fragment.
Study coevolutionary trading-agent dynamics in continuous strategies.
problem Understanding adaptive trading-agent interactions in complex markets.
method Experimental study of adaptive automated trading agents in a continuous strategy space.
result High-dimensional coevolutionary dynamics pose challenges in market analysis.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
Meta-learning improves neural networks by adapting learning algorithms.
problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.
metric-learn simplifies metric learning in Python.
problem Performing distance metric learning efficiently.
method Unified scikit-learn compatible interface for supervised and weakly-supervised metric learning.
result Unified interface for cross-validation and model selection.
Meta-learning speeds up learning new tasks.
problem Designing and improving machine learning pipelines.
method Observing and learning from different machine learning approaches.
result Learning new tasks much faster than traditional methods.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Machine learning models adapt to motor learning but face challenges.
problem Adapting machine learning to handle motor variability and differentiate new movements from known ones.
method Parameter adaptation, transfer and meta-learning, reinforcement learning.
result Challenges in applying machine learning models for motor learning support systems.
Dropout learning is analyzed as ensemble learning to prevent overfitting.
problem Overfitting in deep learning models.
method Dropout learning ignores some inputs and hidden units with a probability, p, and combines them with the learned network.
result Combining neglected hidden units with the learned network can be seen as ensemble learning.
Optimal learning paths designed for E-learning systems using reinforcement learning.
problem Designing optimal learning paths for E-learning systems.
method Developed a hierarchical skill model and a proficiency level model, applied reinforcement learning to find the optimal learning strategy.
result Demonstrated the effectiveness of the proposed framework via numerical experiments.
New theory improves deep learning performance without statistical assumptions.
problem Improving deep learning performance without statistical assumptions.
method Measure-theoretic theory for machine learning, derived regularization method.
result New regularization method outperforms previous methods in various datasets.
Dex improves reinforcement learning by solving complex environments incrementally.
problem Training reinforcement learning agents for complex, ever-changing environments.
method Incremental learning approach, using optimal weights from simpler environments.
result Incremental learning yields superior performance across multiple Dex environments.
HGAIL learns policies without expert demonstrations.
problem Lack of expert demonstrations in imitation learning.
method Combines hindsight and GAIL to learn policies.
result Comparable performance to current methods, with curriculum learning.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
Unsupervised meta-learning speeds up reinforcement learning tasks.
problem Efficiently solving new reinforcement learning tasks.
method Formulating unsupervised meta-reinforcement learning and using mutual information for task proposals.
result Unsupervised meta-reinforcement learning effectively acquires accelerated procedures without manual task design.
Pymc-learn simplifies probabilistic machine learning for non-specialists.
problem Making probabilistic machine learning accessible to non-experts.
method Inspired by scikit-learn, Pymc-learn provides a high-level language for probabilistic models.
result Pymc-learn brings probabilistic machine learning to non-specialists with ease, performance, and flexibility.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Paper discusses flaws in traditional RL for lifelong learning.
problem Traditional RL fails to model lifelong learning systems.
method Simplified prototype of lifelong RL system.
result Insights into lifelong RL, showing traditional RL's limitations.
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).
New unsupervised learning technique learns independent kernels for better machine learning tasks.
problem Improving unsupervised representation learning for machine learning tasks.
method Stacking convolutional transforms using alternating proximal minimization scheme.
result DCTL outperforms shallow version CTL on benchmark datasets.
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
Meta-learning helps models learn quickly from few samples.
problem Deep learning requires many samples, which are hard to get.
method Meta-learning optimizes models to adapt quickly to new tasks.
result Meta-learning can improve model efficiency and adaptability.