Search Results for author:
Found 48 papers, 17 papers with code
Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms
In this paper we propose and investigate a wide class of Mirror Descent updates (MD) and associated novel Generalized Exponentiated Gradient (GEG) algorithms by exploiting various trace-form entropies and associated deformed logarithms and their inverses - deformed (generalized) exponential functions.
Generalized Exponentiated Gradient Algorithms Using the Euler Two-Parameter Logarithm
In order to derive novel GEG/MD updates, we estimate generalized exponential function, which closely approximates the inverse of the Euler two-parameter logarithm.
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-Flow.
Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection
This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function.
Quantization Aware Factorization for Deep Neural Network Compression
Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks.
Optical Coherence Tomography Image Enhancement via Block Hankelization and Low Rank Tensor Network Approximation
The low resolution image was first patch Hankelized and then its Tensor Ring decomposition with rank incremental has been computed.
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition
Pedestrian Attribute Recognition (PAR) deals with the problem of identifying features in a pedestrian image.
AnoOnly: Semi-Supervised Anomaly Detection with the Only Loss on Anomalies
Unlike existing SSAD methods that resort to strict loss supervision, AnoOnly suspends it and introduces a form of weak supervision for normal data.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
+1
Image Reconstruction using Superpixel Clustering and Tensor Completion
This paper presents a pixel selection method for compact image representation based on superpixel segmentation and tensor completion.
Tensor Networks Meet Neural Networks: A Survey and Future Perspectives
Interestingly, although these two types of networks originate from different observations, they are inherently linked through the common multilinearity structure underlying both TNs and NNs, thereby motivating a significant number of intellectual developments regarding combinations of TNs and NNs.
TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
We present a novel procedure for optimization based on the combination of efficient quantized tensor train representation and a generalized maximum matrix volume principle.
How to Train Unstable Looped Tensor Network
This motivates using a hybrid model of CPD and TKD, a decomposition with multiple Tucker models with small core tensor, known as block term decomposition (BTD).
L3C-Stereo: Lossless Compression for Stereo Images
To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module.
CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network
In this work, the coupled-translation fusion network (CTFN) is firstly proposed to model bi-direction interplay via couple learning, ensuring the robustness in respect to missing modalities.
Meta-Solver for Neural Ordinary Differential Equations
Moreover, we show that the right choice of solver parameterization can significantly affect neural ODEs models in terms of robustness to adversarial attacks.
Improving EEG Decoding via Clustering-based Multi-task Feature Learning
With the encoded label matrix, we devise a novel multi-task learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses.
Deep Learning in EEG: Advance of the Last Ten-Year Critical Period
Deep learning has achieved excellent performance in a wide range of domains, especially in speech recognition and computer vision.
Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Most state of the art deep neural networks are overparameterized and exhibit a high computational cost.
Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles
We describe various aspects of multiple human intelligences and learning styles, which may impact on a variety of AI problem domains.
Towards Understanding Normalization in Neural ODEs
Normalization is an important and vastly investigated technique in deep learning.
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs
We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models.
Using Reinforcement Learning in the Algorithmic Trading Problem
A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures.
Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting
This work proposes a novel approach for multiple time series forecasting.
Reduced-Order Modeling of Deep Neural Networks
We introduce a new method for speeding up the inference of deep neural networks.
Manifold Modeling in Embedded Space: A Perspective for Interpreting "Deep Image Prior"
The proposed approach is dividing the convolution into ``delay-embedding'' and ``transformation (\ie encoder-decoder)'', and proposing a simple, but essential, image/tensor modeling method which is closely related to dynamical systems and self-similarity.
Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
The proposed approach is dividing the convolution into ``delay-embedding'' and ``transformation (\ie encoder-decoder)'', and proposing a simple, but essential, image/tensor modeling method which is closely related to dynamical systems and self-similarity.
Multi-Kernel Capsule Network for Schizophrenia Identification
Methods: To overcome the aforementioned drawbacks, we proposed a multi-kernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure.
MUSCO: Multi-Stage Compression of neural networks
The low-rank tensor approximation is very promising for the compression of deep neural networks.
Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization
Nonsmooth Nonnegative Matrix Factorization (nsNMF) is capable of producing more localized, less overlapped feature representations than other variants of NMF while keeping satisfactory fit to data.
Quadratic Programming Over Ellipsoids (with Applications to Constrained Linear Regression and Tensor Decomposition)
A novel algorithm to solve the quadratic programming problem over ellipsoids is proposed.
Optimization and Control
Tensor Ring Decomposition
In this paper, we introduce a fundamental tensor decomposition model to represent a large dimensional tensor by a circular multilinear products over a sequence of low dimensional cores, which can be graphically interpreted as a cyclic interconnection of 3rd-order tensors, and thus termed as tensor ring (TR) decomposition.
Linked Component Analysis from Matrices to High Order Tensors: Applications to Biomedical Data
With the increasing availability of various sensor technologies, we now have access to large amounts of multi-block (also called multi-set, multi-relational, or multi-view) data that need to be jointly analyzed to explore their latent connections.
Smooth PARAFAC Decomposition for Tensor Completion
The proposed method admits significant advantages, owing to the integration of smooth PARAFAC decomposition for incomplete tensors and the efficient selection of models in order to minimize the tensor rank.
Bayesian Sparse Tucker Models for Dimension Reduction and Tensor Completion
Tucker decomposition is the cornerstone of modern machine learning on tensorial data analysis, which have attracted considerable attention for multiway feature extraction, compressive sensing, and tensor completion.
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.
Canonical Polyadic Decomposition with Auxiliary Information for Brain Computer Interface
Unlike vector-based methods that destroy data structure, Canonical Polyadic Decomposition (CPD) aims to process physiological signals in the form of multi-way array, which considers relationships between dimensions and preserves structure information contained by the physiological signal.
Bayesian Robust Tensor Factorization for Incomplete Multiway Data
We propose a generative model for robust tensor factorization in the presence of both missing data and outliers.
Multi-tensor Completion for Estimating Missing Values in Video Data
Thus one question raised whether such the relationship can improve the performance of data completion or not?
Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness
Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of data.
Era of Big Data Processing: A New Approach via Tensor Networks and Tensor Decompositions
Such a new emerging technology for multidimensional big data is a multiway analysis via tensor networks (TNs) and tensor decompositions (TDs) which represent tensors by sets of factor (component) matrices and lower-order (core) tensors.
Emerging Technologies
Bayesian CP Factorization of Incomplete Tensors with Automatic Rank Determination
CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors.
Frequency Recognition in SSVEP-based BCI using Multiset Canonical Correlation Analysis
Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs).
Tensor Decompositions: A New Concept in Brain Data Analysis?
Keywords: Multilinear BSS, linked multiway BSS/ICA, tensor factorizations and decompositions, constrained Tucker and CP models, Penalized Tensor Decompositions (PTD), feature extraction, classification, multiway PLS and CCA.
Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction
Very often data we encounter in practice is a collection of matrices rather than a single matrix.
Accelerated Canonical Polyadic Decomposition by Using Mode Reduction
Canonical Polyadic (or CANDECOMP/PARAFAC, CP) decompositions (CPD) are widely applied to analyze high order tensors.
Higher-Order Partial Least Squares (HOPLS): A Generalized Multi-Linear Regression Method
A new generalized multilinear regression model, termed the Higher-Order Partial Least Squares (HOPLS), is introduced with the aim to predict a tensor (multiway array) $\tensor{Y}$ from a tensor $\tensor{X}$ through projecting the data onto the latent space and performing regression on the corresponding latent variables.
