scholarly journals Completely Heterogeneous Transfer Learning with Attention - What And What Not To Transfer

2017 ◽  
Author(s):  
Seungwhan Moon ◽  
Jaime Carbonell
Keyword(s):  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
A Priori ◽  
Classification Task ◽  
Learning Approach ◽  
Learning Framework ◽  
Previous State

We study a transfer learning framework where source and target datasets are heterogeneous in both feature and label spaces. Specifically, we do not assume explicit relations between source and target tasks a priori, and thus it is crucial to determine what and what not to transfer from source knowledge. Towards this goal, we define a new heterogeneous transfer learning approach that (1) selects and attends to an optimized subset of source samples to transfer knowledge from, and (2) builds a unified transfer network that learns from both source and target knowledge. This method, termed "Attentional Heterogeneous Transfer", along with a newly proposed unsupervised transfer loss, improve upon the previous state-of-the-art approaches on extensive simulations as well as a challenging hetero-lingual text classification task.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

scholarly journals A structure-based deep learning framework for protein engineering

2019 ◽  
Author(s):  
Raghav Shroff ◽  
Austin W. Cole ◽  
Barrett R. Morrow ◽  
Daniel J. Diaz ◽  
Isaac Donnell ◽  
...  
Keyword(s):  
Neural Network ◽  
Amino Acids ◽  
Deep Learning ◽  
Protein Engineering ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
A Priori ◽  
Novel Proteins ◽  
Learning Framework

AbstractWhile deep learning methods exist to guide protein optimization, examples of novel proteins generated with these techniques require a priori mutational data. Here we report a 3D convolutional neural network that associates amino acids with neighboring chemical microenvironments at state-of-the-art accuracy. This algorithm enables identification of novel gain-of-function mutations, and subsequent experiments confirm substantive phenotypic improvements in stability-associated phenotypes in vivo across three diverse proteins.

Text Classification Using Compression-Based Dissimilarity Measures

2015 ◽  
Vol 29 (05) ◽  
pp. 1553004 ◽  
Author(s):  
David Pereira Coutinho ◽  
Mário A. T. Figueiredo
Keyword(s):  
Text Classification ◽  
Nearest Neighbor ◽  
State Of The Art ◽  
Feature Space ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Feature Engineering ◽  
Dissimilarity Measures ◽  
Previous State ◽  
Art Techniques

Arguably, the most difficult task in text classification is to choose an appropriate set of features that allows machine learning algorithms to provide accurate classification. Most state-of-the-art techniques for this task involve careful feature engineering and a pre-processing stage, which may be too expensive in the emerging context of massive collections of electronic texts. In this paper, we propose efficient methods for text classification based on information-theoretic dissimilarity measures, which are used to define dissimilarity-based representations. These methods dispense with any feature design or engineering, by mapping texts into a feature space using universal dissimilarity measures; in this space, classical classifiers (e.g. nearest neighbor or support vector machines) can then be used. The reported experimental evaluation of the proposed methods, on sentiment polarity analysis and authorship attribution problems, reveals that it approximates, sometimes even outperforms previous state-of-the-art techniques, despite being much simpler, in the sense that they do not require any text pre-processing or feature engineering.

scholarly journals Dual Adversarial Co-Learning for Multi-Domain Text Classification

2020 ◽  
Vol 34 (04) ◽  
pp. 6438-6445
Author(s):  
Yuan Wu ◽  
Yuhong Guo
Keyword(s):  
Text Classification ◽  
State Of The Art ◽  
Digital Data ◽  
Classification Model ◽  
Classification Models ◽  
Learning Framework ◽  
Good Classification ◽  
Classification Tasks ◽  
Multiple Domains ◽  
Learned Features

With the advent of deep learning, the performance of text classification models have been improved significantly. Nevertheless, the successful training of a good classification model requires a sufficient amount of labeled data, while it is always expensive and time consuming to annotate data. With the rapid growth of digital data, similar classification tasks can typically occur in multiple domains, while the availability of labeled data can largely vary across domains. Some domains may have abundant labeled data, while in some other domains there may only exist a limited amount (or none) of labeled data. Meanwhile text classification tasks are highly domain-dependent — a text classifier trained in one domain may not perform well in another domain. In order to address these issues, in this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.

scholarly journals Generalization in data-driven models of primary visual cortex

2020 ◽  
Author(s):  
Konstantin-Klemens Lurz ◽  
Mohammad Bashiri ◽  
Konstantin Willeke ◽  
Akshay K. Jagadish ◽  
Eric Wang ◽  
...  
Keyword(s):  
Visual Cortex ◽  
Transfer Learning ◽  
Primary Visual Cortex ◽  
State Of The Art ◽  
Response Prediction ◽  
Data Driven ◽  
Convolutional Network ◽  
The Core ◽  
Current Task ◽  
Previous State

AbstractDeep neural networks (DNN) have set new standards at predicting responses of neural populations to visual input. Most such DNNs consist of a convolutional network (core) shared across all neurons which learns a representation of neural computation in visual cortex and a neuron-specific readout that linearly combines the relevant features in this representation. The goal of this paper is to test whether such a representation is indeed generally characteristic for visual cortex, i.e. generalizes between animals of a species, and what factors contribute to obtaining such a generalizing core. To push all non-linear computations into the core where the generalizing cortical features should be learned, we devise a novel readout that reduces the number of parameters per neuron in the readout by up to two orders of magnitude compared to the previous state-of-the-art. It does so by taking advantage of retinotopy and learns a Gaussian distribution over the neuron’s receptive field position. With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network. We then investigate whether the convolutional core indeed captures general cortical features by using the core in transfer learning to a different animal. When transferring a core trained on thousands of neurons from various animals and scans we exceed the performance of training directly on that animal by 12%, and outperform a commonly used VGG16 core pre-trained on imagenet by 33%. In addition, transfer learning with our data-driven core is more data-efficient than direct training, achieving the same performance with only 40% of the data. Our model with its novel readout thus sets a new state-of-the-art for neural response prediction in mouse visual cortex from natural images, generalizes between animals, and captures better characteristic cortical features than current task-driven pre-training approaches such as VGG16.

scholarly journals Deep learning for COVID-19 detection based on CT images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Wentao Zhao ◽  
Wei Jiang ◽  
Xinguo Qiu
Keyword(s):  
State Of The Art ◽  
A Priori ◽  
Ct Images ◽  
Learning Approach ◽  
Medical Systems ◽  
Chain Reaction ◽  
Polymerase Chain Reaction Testing ◽  
Computed Tomography Images ◽  
Satisfactory Performance ◽  
Polymerase Chain

AbstractCOVID-19 has tremendously impacted patients and medical systems globally. Computed tomography images can effectively complement the reverse transcription-polymerase chain reaction testing. This study adopted a convolutional neural network for COVID-19 testing. We examined the performance of different pre-trained models on CT testing and identified that larger, out-of-field datasets boost the testing power of the models. This suggests that a priori knowledge of the models from out-of-field training is also applicable to CT images. The proposed transfer learning approach proves to be more successful than the current approaches described in literature. We believe that our approach has achieved the state-of-the-art performance in identification thus far. Based on experiments with randomly sampled training datasets, the results reveal a satisfactory performance by our model. We investigated the relevant visual characteristics of the CT images used by the model; these may assist clinical doctors in manual screening.

scholarly journals Mind Your Language: Abuse and Offense Detection for Code-Switched Languages

2019 ◽  
Vol 33 ◽  
pp. 9951-9952 ◽  
Author(s):  
Raghav Kapoor ◽  
Yaman Kumar ◽  
Kshitij Rajput ◽  
Rajiv Ratn Shah ◽  
Ponnurangam Kumaraguru ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Text Classification ◽  
Hate Speech ◽  
State Of The Art ◽  
Indian Subcontinent ◽  
The State ◽  
Speech Classification ◽  
Multilingual Societies

In multilingual societies like the Indian subcontinent, use of code-switched languages is much popular and convenient for the users. In this paper, we study offense and abuse detection in the code-switched pair of Hindi and English (i.e, Hinglish), the pair that is the most spoken. The task is made difficult due to non-fixed grammar, vocabulary, semantics and spellings of Hinglish language. We apply transfer learning and make a LSTM based model for hate speech classification. This model surpasses the performance shown by the current best models to establish itself as the state-of-the-art in the unexplored domain of Hinglish offensive text classification. We also release our model and the embeddings trained for research purposes.

scholarly journals An Active Learning Approach with Uncertainty, Representativeness, and Diversity

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Tianxu He ◽  
Shukui Zhang ◽  
Jie Xin ◽  
Pengpeng Zhao ◽  
Jian Wu ◽  
...  
Keyword(s):  
Active Learning ◽  
Clustering Algorithm ◽  
Ad Hoc ◽  
State Of The Art ◽  
The Internet ◽  
Learning Approach ◽  
Learning Approaches ◽  
Learning Framework ◽  
Query Selection ◽  
The Internet Of Things

Big data from the Internet of Things may create big challenge for data classification. Most active learning approaches select either uncertain or representative unlabeled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criteria for query selection, they are usually ad hoc in finding unlabeled instances that are both informative and representative and fail to take the diversity of instances into account. We address this challenge by presenting a new active learning framework which considers uncertainty, representativeness, and diversity creation. The proposed approach provides a systematic way for measuring and combining the uncertainty, representativeness, and diversity of an instance. Firstly, use instances’ uncertainty and representativeness to constitute the most informative set. Then, use the kernelk-means clustering algorithm to filter the redundant samples and the resulting samples are queried for labels. Extensive experimental results show that the proposed approach outperforms several state-of-the-art active learning approaches.

scholarly journals Convolutional Neural Networks for Classifying Melanoma Images

2020 ◽  
Author(s):  
Abhinav Sagar ◽  
J Dheeba
Keyword(s):  
Neural Networks ◽  
Skin Cancer ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Cancer Classification ◽  
Previous State ◽  
Better Than

AbstractIn this work, we address the problem of skin cancer classification using convolutional neural networks. A lot of cancer cases early on are misdiagnosed as something else leading to severe consequences including the death of a patient. Also there are cases in which patients have some other problems and doctors think they might have skin cancer. This leads to unnecessary time and money spent for further diagnosis. In this work, we address both of the above problems using deep neural networks and transfer learning architecture. We have used publicly available ISIC databases for both training and testing our model. Our work achieves an accuracy of 0.935, precision of 0.94, recall of 0.77, F1 score of 0.85 and ROC-AUC of 0.861 which is better than the previous state of the art approaches.

scholarly journals Self-supervised Regularization for Text Classification

2021 ◽  
Vol 9 ◽  
pp. 641-656
Author(s):  
Meng Zhou ◽  
Zechen Li ◽  
Pengtao Xie
Keyword(s):  
Text Classification ◽  
Real World ◽  
Input Data ◽  
Supervised Classification ◽  
Classification Task ◽  
Learning Approach ◽  
Classification Models ◽  
Data Representations ◽  
Class Labels ◽  
Real World Problems

Abstract Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL (Devlin et al., 2019a) is an unsupervised learning approach that defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human- provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg.

Sign in / Sign up

Export Citation Format

Share Document