Search Results for author:
Found 10 papers, 0 papers with code
One-Shot Domain Incremental Learning
In DIL, we assume that samples on new domains are observed over time.
Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and the mean of the activation vector in the previous layer.
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
We propose an accuracy-preserving calibration method using the Concrete distribution as the probabilistic model on the probability simplex.
How many views does your deep neural network use for prediction?
The generalization ability of Deep Neural Networks (DNNs) is still not fully understood, despite numerous theoretical and empirical analyses.
Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts
Distribution shifts are problems where the distribution of data changes between training and testing, which can significantly degrade the performance of a model deployed in the real world.
StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Space
One major challenge in machine learning applications is coping with mismatches between the datasets used in the development and those obtained in real-world applications.
Neural Time Warping For Multiple Sequence Alignment
Multiple sequences alignment (MSA) is a traditional and challenging task for time-series analyses.
Flow-based Image-to-Image Translation with Feature Disentanglement
Learning non-deterministic dynamics and intrinsic factors from images obtained through physical experiments is at the intersection of machine learning and material science.
Neural Edit Operations for Biological Sequences
The evolution of biological sequences, such as proteins or DNAs, is driven by the three basic edit operations: substitution, insertion, and deletion.
Linearly Constrained Weights: Resolving the Vanishing Gradient Problem by Reducing Angle Bias
In this paper, we first identify \textit{angle bias}, a simple but remarkable phenomenon that causes the vanishing gradient problem in a multilayer perceptron (MLP) with sigmoid activation functions.
