Search Results for author:
Found 12 papers, 1 papers with code
Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps
Despite the recent progress in few-shot learning, most methods rely on supervised pretraining or meta-learning on labeled meta-training data and cannot be applied to the case where the pretraining data is unlabeled.
Self-Supervised Learning
Unsupervised Few-Shot Image Classification
+1
Quantum-Inspired Tensor Neural Networks for Partial Differential Equations
We demonstrate that TNN provide significant parameter savings while attaining the same accuracy as compared to the classical Dense Neural Network (DNN).
Don't overfit the history -- Recursive time series data augmentation
We apply RIM to diverse real world time series cases to achieve strong performance over non-augmented data on regression, classification, and reinforcement learning tasks.
Meta-free few-shot learning via representation learning with weight averaging
To tackle the aforementioned issues, we propose a new transfer learning method to obtain accurate and reliable models for few-shot regression and classification.
Risk-Aware Transfer in Reinforcement Learning using Successor Features
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making.
Attentive Gaussian processes for probabilistic time-series generation
We propose a computationally efficient attention-based network combined with the Gaussian process regression to generate real-valued sequence, which we call the Attentive-GP.
Symmetry-Augmented Representation for Time Series
We examine the hypothesis that the concept of symmetry augmentation is fundamentally linked to learning.
Incremental few-shot learning via vector quantization in deep embedded space
For classification problems, we employ the nearest neighbor scheme to make classification on sparsely available data and incorporate intra-class variation, less forgetting regularization and calibration of reference vectors to mitigate catastrophic forgetting.
Ranked #9 on
Few-Shot Class-Incremental Learning
on mini-Imagenet
ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms.
Bayesian Experience Reuse for Learning from Multiple Demonstrators
We demonstrate the effectiveness of this approach for static optimization of smooth functions, and transfer learning in a high-dimensional supply chain problem with cost uncertainty.
Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts
In this paper, we assume knowledge of estimated source task dynamics and policies, and common sub-goals but different dynamics.
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach
Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms.
