Search Results for author: Andrzej Cichocki

Found 34 papers, 10 papers with code

L3C-Stereo: Lossless Compression for Stereo Images

no code implementations21 Aug 2021 Zihao Huang, Zhe Sun, Feng Duan, Andrzej Cichocki, Peiying Ruan, Chao Li

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.

Autonomous Driving

CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network

no code implementations ACL 2021 Jiajia Tang, Kang Li, Xuanyu Jin, Andrzej Cichocki, Qibin Zhao, Wanzeng Kong

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.

Multimodal Sentiment Analysis

Meta-Solver for Neural Ordinary Differential Equations

1 code implementation15 Mar 2021 Julia Gusak, Alexandr Katrutsa, Talgat Daulbaev, Andrzej Cichocki, Ivan Oseledets

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

no code implementations12 Dec 2020 Yu Zhang, Tao Zhou, Wei Wu, Hua Xie, Hongru Zhu, Guoxu Zhou, Andrzej Cichocki

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.

EEG Eeg Decoding +1

Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

no code implementations22 Nov 2020 Shu Gong, Kaibo Xing, Andrzej Cichocki, Junhua Li

Deep learning has achieved excellent performance in a wide range of domains, especially in speech recognition and computer vision.

EEG Emotion Recognition +1

Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles

no code implementations7 Aug 2020 Andrzej Cichocki, Alexander P. Kuleshov

We describe various aspects of multiple human intelligences and learning styles, which may impact on a variety of AI problem domains.

Decision Making Meta-Learning

Using Reinforcement Learning in the Algorithmic Trading Problem

1 code implementation26 Feb 2020 Evgeny Ponomarev, Ivan Oseledets, Andrzej Cichocki

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.

Algorithmic Trading

Reduced-Order Modeling of Deep Neural Networks

no code implementations15 Oct 2019 Julia Gusak, Talgat Daulbaev, Evgeny Ponomarev, Andrzej Cichocki, Ivan Oseledets

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

1 code implementation8 Aug 2019 Tatsuya Yokota, Hidekata Hontani, Qibin Zhao, Andrzej Cichocki

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.

Denoising Image Reconstruction +2

Multi-Kernel Capsule Network for Schizophrenia Identification

no code implementations30 Jul 2019 Tian Wang, Anastasios Bezerianos, Andrzej Cichocki, Junhua Li

Methods: To overcome the aforementioned drawbacks, we proposed a multi-kernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure.

Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization

no code implementations20 Mar 2018 Jinshi Yu, Guoxu Zhou, Andrzej Cichocki, Shengli Xie

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)

no code implementations13 Nov 2017 Anh-Huy Phan, Masao Yamagishi, Danilo Mandic, Andrzej Cichocki

A novel algorithm to solve the quadratic programming problem over ellipsoids is proposed.

Optimization and Control

Tensor Ring Decomposition

no code implementations17 Jun 2016 Qibin Zhao, Guoxu Zhou, Shengli Xie, Liqing Zhang, Andrzej Cichocki

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.

Tensor Decomposition Tensor Networks

Linked Component Analysis from Matrices to High Order Tensors: Applications to Biomedical Data

no code implementations29 Aug 2015 Guoxu Zhou, Qibin Zhao, Yu Zhang, Tülay Adalı, Shengli Xie, Andrzej Cichocki

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.

Tensor Decomposition

Smooth PARAFAC Decomposition for Tensor Completion

no code implementations25 May 2015 Tatsuya Yokota, Qibin Zhao, Andrzej Cichocki

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.

Matrix Completion

Bayesian Sparse Tucker Models for Dimension Reduction and Tensor Completion

1 code implementation10 May 2015 Qibin Zhao, Liqing Zhang, Andrzej Cichocki

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.

Compressive Sensing Dimensionality Reduction +1

Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements

no code implementations6 Mar 2015 Wenfei Cao, Yao Wang, Jian Sun, Deyu Meng, Can Yang, Andrzej Cichocki, Zongben Xu

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

no code implementations23 Oct 2014 Junhua Li, Chao Li, Andrzej Cichocki

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.

Classification EEG +1

Bayesian Robust Tensor Factorization for Incomplete Multiway Data

no code implementations9 Oct 2014 Qibin Zhao, Guoxu Zhou, Liqing Zhang, Andrzej Cichocki, Shun-ichi Amari

We propose a generative model for robust tensor factorization in the presence of both missing data and outliers.

Model Selection Variational Inference

Feature Learning from Incomplete EEG with Denoising Autoencoder

no code implementations3 Oct 2014 Junhua Li, Zbigniew Struzik, Liqing Zhang, Andrzej Cichocki

An alternative pathway for the human brain to communicate with the outside world is by means of a brain computer interface (BCI).

Denoising EEG

Multi-tensor Completion for Estimating Missing Values in Video Data

no code implementations1 Sep 2014 Chao Li, Lili Guo, Andrzej Cichocki

Thus one question raised whether such the relationship can improve the performance of data completion or not?

Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness

no code implementations17 Apr 2014 Guoxu Zhou, Andrzej Cichocki, Qibin Zhao, Shengli Xie

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

no code implementations9 Mar 2014 Andrzej Cichocki

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

1 code implementation25 Jan 2014 Qibin Zhao, Liqing Zhang, Andrzej Cichocki

CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors.

Bayesian Inference Image Inpainting

Frequency Recognition in SSVEP-based BCI using Multiset Canonical Correlation Analysis

no code implementations26 Aug 2013 Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki

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?

no code implementations2 May 2013 Andrzej Cichocki

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.

Classification Dimensionality Reduction +1

Accelerated Canonical Polyadic Decomposition by Using Mode Reduction

no code implementations15 Nov 2012 Guoxu Zhou, Andrzej Cichocki, Shengli Xie

Canonical Polyadic (or CANDECOMP/PARAFAC, CP) decompositions (CPD) are widely applied to analyze high order tensors.

Dimensionality Reduction

Higher-Order Partial Least Squares (HOPLS): A Generalized Multi-Linear Regression Method

1 code implementation5 Jul 2012 Qibin Zhao, Cesar F. Caiafa, Danilo P. Mandic, Zenas C. Chao, Yasuo Nagasaka, Naotaka Fujii, Liqing Zhang, Andrzej Cichocki

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.