Search Results for author:
Found 25 papers, 11 papers with code
Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model
However, when the training dataset is class-imbalanced, some NC properties will no longer be true.
Unveiling Comparative Sentiments in Vietnamese Product Reviews: A Sequential Classification Framework
Comparative opinion mining is a specialized field of sentiment analysis that aims to identify and extract sentiments expressed comparatively.
Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
Specifically, via a non-trivial theoretical analysis of linear conditional VAE and hierarchical VAE with two levels of latent, we prove that the cause of posterior collapses in these models includes the correlation between the input and output of the conditional VAE and the effect of learnable encoder variance in the hierarchical VAE.
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing.
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
Graph Neural Networks (GNNs) had been demonstrated to be inherently susceptible to the problems of over-smoothing and over-squashing.
Improving Generative Flow Networks with Path Regularization
Generative Flow Networks (GFlowNets) are recently proposed models for learning stochastic policies that generate compositional objects by sequences of actions with the probability proportional to a given reward function.
Hierarchical Sliced Wasserstein Distance
We explain the usage of these projections by introducing Hierarchical Radon Transform (HRT) which is constructed by applying Radon Transform variants recursively.
Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence.
Transformer with Fourier Integral Attentions
Multi-head attention empowers the recent success of transformers, the state-of-the-art models that have achieved remarkable success in sequence modeling and beyond.
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs).
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
In this paper, we propose Point-Unet, a novel method that incorporates the efficiency of deep learning with 3D point clouds into volumetric segmentation.
How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
As case studies, we consider how momentum can improve the architecture design for recurrent neural networks (RNNs), neural ordinary differential equations (ODEs), and transformers.
SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation
Both automatic and human evaluation demonstrated that our approach can generate poems that have better cohesion without losing the quality due to additional loss.
Neural Networks with Recurrent Generative Feedback
This mechanism can be interpreted as a form of self-consistency between the maximum a posteriori (MAP) estimation of an internal generative model and the external environment.
Sample Efficient Graph-Based Optimization with Noisy Observations
We study sample complexity of optimizing "hill-climbing friendly" functions defined on a graph under noisy observations.
Greedy Convex Ensemble
Theoretically, we first consider whether we can use linear, instead of convex, combinations, and obtain generalization results similar to existing ones for learning from a convex hull.
Brain-inspired Robust Vision using Convolutional Neural Networks with Feedback
Primates have a remarkable ability to correctly classify images even in the presence of significant noise and degradation.
Out-of-Distribution Detection Using Neural Rendering Generative Models
Our results show that when trained on CIFAR-10, lower likelihood (of latent variables) is assigned to SVHN images.
Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference
State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications.
Neural Rendering Model: Joint Generation and Prediction for Semi-Supervised Learning
The conjugate prior yields a new regularizer for learning based on the paths rendered in the generative model for training CNNs–the Rendering Path Normalization (RPN).
A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
This conjugate prior yields a new regularizer based on paths rendered in the generative model for training CNNs-the Rendering Path Normalization (RPN).
EnergyNet: Energy-Efficient Dynamic Inference
The prohibitive energy cost of running high-performance Convolutional Neural Networks (CNNs) has been limiting their deployment on resource-constrained platforms including mobile and wearable devices.
A Probabilistic Framework for Deep Learning
We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables.
Semi-Supervised Learning with the Deep Rendering Mixture Model
Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning.
A Probabilistic Theory of Deep Learning
A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation.
