Search Results for author: Stan Matwin

Found 46 papers, 10 papers with code

Evolutionary Augmentation Policy Optimization for Self-supervised Learning

no code implementations2 Mar 2023 Noah Barrett, Zahra Sadeghi, Stan Matwin

We also compare optimal SSL solutions found by our evolutionary search mechanism and show the effect of batch size in the pretext task on two visual datasets.

Data Augmentation Self-Supervised Learning

A semi-supervised methodology for fishing activity detection using the geometry behind the trajectory of multiple vessels

1 code implementation12 Jul 2022 Martha Dais Ferreira, Gabriel Spadon, Amilcar Soares, Stan Matwin

To this end, we leverage the unsupervised nature of cluster analysis to label the trajectory geometry highlighting the changes in the vessel's moving pattern which tends to indicate fishing activity.

Action Detection Activity Detection +2

Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning

no code implementations24 Feb 2022 Gabriel Spadon, Martha D. Ferreira, Amilcar Soares, Stan Matwin

The oceans are a source of an impressive mixture of complex data that could be used to uncover relationships yet to be discovered.

Survey of Generative Methods for Social Media Analysis

no code implementations13 Dec 2021 Stan Matwin, Aristides Milios, Paweł Prałat, Amilcar Soares, François Théberge

This survey draws a broad-stroke, panoramic picture of the State of the Art (SoTA) of the research in generative methods for the analysis of social media data.

SGORNN: Combining Scalar Gates and Orthogonal Constraints in Recurrent Networks

no code implementations29 Sep 2021 William Keith Taylor-Melanson, Martha Dais Ferreira, Stan Matwin

Our experimental results on the addition problem confirm that our combination of orthogonal and scalar gated RNNs are able to outperform both predecessor models on long sequences using only a single RNN cell.

Language Modelling

Artificial Intelligence for Emotion-Semantic Trending and People Emotion Detection During COVID-19 Social Isolation

no code implementations16 Jan 2021 Hamed Jelodar, Rita Orji, Stan Matwin, Swarna Weerasinghe, Oladapo Oyebode, Yongli Wang

Novelty of the approach presented herein is a multitask methodological framework of text data processing, implemented as a pipeline for meaningful emotion detection and analysis, based on the Plutchik/Ekman approach to emotion detection and trend detection.

Medical Diagnosis

Learn Faster and Forget Slower via Fast and Stable Task Adaptation

no code implementations2 Jul 2020 Farshid Varno, Lucas May Petry, Lisa Di Jorio, Stan Matwin

We empirically show that compared to prevailing fine-tuning practices, FAST learns the target task faster and forgets the source task slower.

Transfer Learning

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

1 code implementation ICML 2020 Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei

We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment perspective.

Pseudo Label Unsupervised Domain Adaptation

Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning

no code implementations7 Apr 2020 Lucas May Petry, Amilcar Soares, Vania Bogorny, Bruno Brandoli, Stan Matwin

The global expansion of maritime activities and the development of the Automatic Identification System (AIS) have driven the advances in maritime monitoring systems in the last decade.

Anomaly Detection BIG-bench Machine Learning +1

Using Deep Reinforcement Learning Methods for Autonomous Vessels in 2D Environments

1 code implementation23 Mar 2020 Mohammad Etemad, Nader Zare, Mahtab Sarvmaili, Amilcar Soares, Bruno Brandoli Machado, Stan Matwin

Experimental results show that the proposed method enhanced the performance of VVN by 55. 31 on average for long-distance missions.

Decision Making Q-Learning +2

Performance of a Deep Neural Network at Detecting North Atlantic Right Whale Upcalls

no code implementations24 Jan 2020 Oliver S. Kirsebom, Fabio Frazao, Yvan Simard, Nathalie Roy, Stan Matwin, Samuel Giard

Passive acoustics provides a powerful tool for monitoring the endangered North Atlantic right whale ($Eubalaena$ $glacialis$), but robust detection algorithms are needed to handle diverse and variable acoustic conditions and differences in recording techniques and equipment.

Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples

no code implementations3 Sep 2019 Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

We use several state-of-the-art embedding techniques including BERT, FastText, and Doc2VecC for the text representation learning and WaveNet and VGG-ish models for audio encoding.

Multimodal Deep Learning Representation Learning +1

Unsupervised Behavior Change Detection in Multidimensional Data Streams for Maritime Traffic Monitoring

no code implementations14 Aug 2019 Lucas May Petry, Amilcar Soares, Vania Bogorny, Stan Matwin

The worldwide growth of maritime traffic and the development of the Automatic Identification System (AIS) has led to advances in monitoring systems for preventing vessel accidents and detecting illegal activities.

BIG-bench Machine Learning Event Detection +1

Using Attention-based Bidirectional LSTM to Identify Different Categories of Offensive Language Directed Toward Female Celebrities

no code implementations WS 2019 Sima Sharifirad, Stan Matwin

In addition, we identify ten female figures from different professions and racial backgrounds who have experienced harassment on Twitter.

Marine Mammal Species Classification using Convolutional Neural Networks and a Novel Acoustic Representation

no code implementations30 Jul 2019 Mark Thomas, Bruce Martin, Katie Kowarski, Briand Gaudet, Stan Matwin

Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes.

General Classification Transfer Learning

Efficient Neural Task Adaptation by Maximum Entropy Initialization

no code implementations25 May 2019 Farshid Varno, Behrouz Haji Soleimani, Marzie Saghayi, Lisa Di Jorio, Stan Matwin

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples.

Transfer Learning

Learning to Learn with Conditional Class Dependencies

no code implementations ICLR 2019 Xiang Jiang, Mohammad Havaei, Farshid Varno, Gabriel Chartrand, Nicolas Chapados, Stan Matwin

Neural networks can learn to extract statistical properties from data, but they seldom make use of structured information from the label space to help representation learning.

Few-Shot Learning Representation Learning

Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection

1 code implementation13 Feb 2019 Duong Nguyen, Oliver S. Kirsebom, Fábio Frazão, Ronan Fablet, Stan Matwin

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection.

Acoustic Novelty Detection Feature Engineering

2-D Embedding of Large and High-dimensional Data with Minimal Memory and Computational Time Requirements

no code implementations4 Feb 2019 Witold Dzwinel, Rafal Wcislo, Stan Matwin

In the advent of big data era, interactive visualization of large data sets consisting of M*10^5+ high-dimensional feature vectors of length N (N ~ 10^3+), is an indispensable tool for data exploratory analysis.

How is Your Mood When Writing Sexist tweets? Detecting the Emotion Type and Intensity of Emotion Using Natural Language Processing Techniques

no code implementations28 Jan 2019 Sima Sharifirad, Borna Jafarpour, Stan Matwin

While sexism has been considered as a category of hateful speech in the literature, there is no comprehensive definition and category of sexism attracting natural language processing techniques.

Sentiment Analysis

Improving the Interpretability of Deep Neural Networks with Knowledge Distillation

no code implementations28 Dec 2018 Xuan Liu, Xiaoguang Wang, Stan Matwin

To tackle this problem, we apply the Knowledge Distillation technique to distill Deep Neural Networks into decision trees in order to attain good performance and interpretability simultaneously.

Ethics Knowledge Distillation +3

Boosting Text Classification Performance on Sexist Tweets by Text Augmentation and Text Generation Using a Combination of Knowledge Graphs

no code implementations WS 2018 Sima Sharifirad, Borna Jafarpour, Stan Matwin

In our text generation approach, we generate new tweets by replacing words using data acquired from ConceptNet relations in order to increase the size of our training set, this method is very helpful with frustratingly small datasets, preserves the label and increases diversity.

Abusive Language BIG-bench Machine Learning +7

On feature selection and evaluation of transportation mode prediction strategies

1 code implementation9 Aug 2018 Mohammad Etemad, Amilcar Soares Junior, Stan Matwin

Since the number of features that may be used to predict a user transportation mode can be substantial, finding a subset of features that maximizes a performance measure is worth investigating.

Decision Making Information Retrieval +2

Predicting Crime Using Spatial Features

no code implementations12 Mar 2018 Fateha Khanam Bappee, Amilcar Soares Junior, Stan Matwin

Our study aims to build a machine learning model for crime prediction using geospatial features for different categories of crime.

Crime Prediction

One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Data

no code implementations25 Feb 2018 Ahmad Pesaranghader, Ali Pesaranghader, Stan Matwin, Marina Sokolova

Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports.

Word Sense Disambiguation

Interpretable Deep Convolutional Neural Networks via Meta-learning

no code implementations2 Feb 2018 Xuan Liu, Xiaoguang Wang, Stan Matwin

We attempt to address this challenge by proposing a technique called CNN-INTE to interpret deep Convolutional Neural Networks (CNN) via meta-learning.

Fairness Meta-Learning

TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

no code implementations7 May 2017 Xiang Jiang, Erico N de Souza, Ahmad Pesaranghader, Baifan Hu, Daniel L. Silver, Stan Matwin

Understanding and discovering knowledge from GPS (Global Positioning System) traces of human activities is an essential topic in mobility-based urban computing.

General Classification

Studying Positive Speech on Twitter

no code implementations24 Feb 2017 Marina Sokolova, Vera Sazonova, Kanyi Huang, Rudraneel Chakraboty, Stan Matwin

In fully automated studies, we tested two approaches: unsupervised statistical analysis, and supervised text classification based on distributed word representation.

General Classification Opinion Mining +2

Reflexive Regular Equivalence for Bipartite Data

no code implementations16 Feb 2017 Aaron Gerow, Mingyang Zhou, Stan Matwin, Feng Shi

Reflexive regular equivalence can also use the structure of transitivities -- in a network sense -- the contribution of which is controlled by the algorithm's only free-parameter, $\alpha$.

Topic Modelling and Event Identification from Twitter Textual Data

no code implementations8 Aug 2016 Marina Sokolova, Kanyi Huang, Stan Matwin, Joshua Ramisch, Vera Sazonova, Renee Black, Chris Orwa, Sidney Ochieng, Nanjira Sambuli

The tremendous growth of social media content on the Internet has inspired the development of the text analytics to understand and solve real-life problems.

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