scholarly journals Data Fine-Tuning

2019 ◽  
Vol 33 ◽  
pp. 8223-8230 ◽  
Author(s):  
Saheb Chhabra ◽  
Puspita Majumdar ◽  
Mayank Vatsa ◽  
Richa Singh
Keyword(s):  
Classification Accuracy ◽  
Fine Tuning ◽  
Model Parameters ◽  
Facial Analysis ◽  
Visual Appearance ◽  
Perturbation Problem ◽  
Black Boxes ◽  
Real World Applications ◽  
Commercial Off The Shelf ◽  
Fine Tune

In real-world applications, commercial off-the-shelf systems are utilized for performing automated facial analysis including face recognition, emotion recognition, and attribute prediction. However, a majority of these commercial systems act as black boxes due to the inaccessibility of the model parameters which makes it challenging to fine-tune the models for specific applications. Stimulated by the advances in adversarial perturbations, this research proposes the concept of Data Fine-tuning to improve the classification accuracy of a given model without changing the parameters of the model. This is accomplished by modeling it as data (image) perturbation problem. A small amount of “noise” is added to the input with the objective of minimizing the classification loss without affecting the (visual) appearance. Experiments performed on three publicly available datasets LFW, CelebA, and MUCT, demonstrate the effectiveness of the proposed concept.

Selectively Fine-Tuning Bayesian Network Learning Algorithm

2016 ◽  
Vol 30 (08) ◽  
pp. 1651005 ◽  
Author(s):  
Amel Alhussan ◽  
Khalil El Hindi
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Classification Accuracy ◽  
Naive Bayes ◽  
Learning Algorithm ◽  
Naïve Bayes ◽  
Fine Tuning ◽  
Network Learning ◽  
Probability Term ◽  
Fine Tune

In this work, we propose a Selective Fine-Tuning algorithm for Bayesian Networks (SFTBN). The aim is to enhance the accuracy of Bayesian Network (BN) classifiers by finding better estimations for the probability terms used by the classifiers. The algorithm augments a BN learning algorithm with a fine-tuning stage that aims to more accurately estimate the probability terms used by the BN. If the value of a probability term causes a misclassification of a training instances and falls outside its valid range then we update (fine-tune) that value. The amount of such an update is proportional to the distance between the value and its valid range. We use the algorithm to fine-tune several forms of BNs: the Naive Bayes (NB), Tree Augmented Naive Bayes (TAN), and Bayesian Augmented Naive Bayes (BAN) models. Our empirical experiments indicate that the SFTBN algorithm improves the classification accuracy of BN classifiers. We also generalized the original fine-tuning algorithm of Naive Bayesian (FTNB) for BN models. We empirically compare the two algorithms, and the empirical results show that while FTNB is more accurate than SFTBN for fine-tuning NB classifiers, SFTBN is more accurate for fine-tuning BNs than the adapted version of FTNB.

scholarly journals Better Fine-Tuning via Instance Weighting for Text Classification

2019 ◽  
Vol 33 ◽  
pp. 7241-7248
Author(s):  
Zhi Wang ◽  
Wei Bi ◽  
Yan Wang ◽  
Xiaojiang Liu
Keyword(s):  
Transfer Learning ◽  
Text Classification ◽  
Fine Tuning ◽  
Model Parameters ◽  
Great Success ◽  
Target Domain ◽  
Instance Weighting ◽  
Training Stage ◽  
Effective Transfer ◽  
Fine Tune

Transfer learning for deep neural networks has achieved great success in many text classification applications. A simple yet effective transfer learning method is to fine-tune the pretrained model parameters. Previous fine-tuning works mainly focus on the pre-training stage and investigate how to pretrain a set of parameters that can help the target task most. In this paper, we propose an Instance Weighting based Finetuning (IW-Fit) method, which revises the fine-tuning stage to improve the final performance on the target domain. IW-Fit adjusts instance weights at each fine-tuning epoch dynamically to accomplish two goals: 1) identify and learn the specific knowledge of the target domain effectively; 2) well preserve the shared knowledge between the source and the target domains. The designed instance weighting metrics used in IW-Fit are model-agnostic, which are easy to implement for general DNN-based classifiers. Experimental results show that IW-Fit can consistently improve the classification accuracy on the target domain.

Fine-Tuning Electronic Properties of Luminescent Pt(II) Complexes via Vertex-Differentiated Coordination of Sterically Invariant Carborane-Based Ligands

2018 ◽  
Author(s):  
Kent O. Kirlikovali ◽  
Jonathan C. Axtell ◽  
Kierstyn Anderson ◽  
Peter I. Djurovich ◽  
Arnold L. Rheingold ◽  
...  
Keyword(s):  
Coordination Chemistry ◽  
Metal Complexes ◽  
Electronic Properties ◽  
Fine Tuning ◽  
Fine Tune

We report the synthesis of two isomeric Pt(II) complexes ligated by doubly deprotonated 1,1′-bis(<i>o</i>-carborane) (<b>bc</b>). This work provides a potential route to fine-tune the electronic properties of luminescent metal complexes by virtue of vertex-differentiated coordination chemistry of carborane-based ligands.

scholarly journals Fine-tuning of a generative neural network for designing multi-target compounds

2021 ◽  
Author(s):  
Thomas Blaschke ◽  
Jürgen Bajorath
Keyword(s):  
Neural Network ◽  
Small Molecules ◽  
De Novo ◽  
Pharmaceutical Research ◽  
Generative Models ◽  
Fine Tuning ◽  
Data Sets ◽  
Single Target ◽  
Fine Tune ◽  
Target Activity

AbstractExploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals A transfer learning framework based on motor imagery rehabilitation for stroke

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fangzhou Xu ◽  
Yunjing Miao ◽  
Yanan Sun ◽  
Dongju Guo ◽  
Jiali Xu ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Motor Imagery ◽  
Stroke Rehabilitation ◽  
Transfer Functions ◽  
Model Parameters ◽  
Transfer Model ◽  
Learning Networks ◽  
Training Time ◽  
Fine Tune ◽  
Bci System

AbstractDeep learning networks have been successfully applied to transfer functions so that the models can be adapted from the source domain to different target domains. This study uses multiple convolutional neural networks to decode the electroencephalogram (EEG) of stroke patients to design effective motor imagery (MI) brain-computer interface (BCI) system. This study has introduced ‘fine-tune’ to transfer model parameters and reduced training time. The performance of the proposed framework is evaluated by the abilities of the models for two-class MI recognition. The results show that the best framework is the combination of the EEGNet and ‘fine-tune’ transferred model. The average classification accuracy of the proposed model for 11 subjects is 66.36%, and the algorithm complexity is much lower than other models.These good performance indicate that the EEGNet model has great potential for MI stroke rehabilitation based on BCI system. It also successfully demonstrated the efficiency of transfer learning for improving the performance of EEG-based stroke rehabilitation for the BCI system.

scholarly journals Lifelong Zero-Shot Learning

2020 ◽  
Author(s):  
Kun Wei ◽  
Cheng Deng ◽  
Xu Yang
Keyword(s):  
Fine Tuning ◽  
Training Set ◽  
Continuous Training ◽  
Evaluation Protocol ◽  
Multiple Datasets ◽  
Real World Applications ◽  
Knowledge Distillation ◽  
Novel Method ◽  
Previous Training ◽  
Current Stage

Zero-Shot Learning (ZSL) handles the problem that some testing classes never appear in training set. Existing ZSL methods are designed for learning from a fixed training set, which do not have the ability to capture and accumulate the knowledge of multiple training sets, causing them infeasible to many real-world applications. In this paper, we propose a new ZSL setting, named as Lifelong Zero-Shot Learning (LZSL), which aims to accumulate the knowledge during the learning from multiple datasets and recognize unseen classes of all trained datasets. Besides, a novel method is conducted to realize LZSL, which effectively alleviates the Catastrophic Forgetting in the continuous training process. Specifically, considering those datasets containing different semantic embeddings, we utilize Variational Auto-Encoder to obtain unified semantic representations. Then, we leverage selective retraining strategy to preserve the trained weights of previous tasks and avoid negative transfer when fine-tuning the entire model. Finally, knowledge distillation is employed to transfer knowledge from previous training stages to current stage. We also design the LZSL evaluation protocol and the challenging benchmarks. Extensive experiments on these benchmarks indicate that our method tackles LZSL problem effectively, while existing ZSL methods fail.

scholarly journals CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning

2020 ◽  
Author(s):  
Yuanrui Dong ◽  
Peng Zhao ◽  
Hanqiao Yu ◽  
Cong Zhao ◽  
Shusen Yang
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Data Privacy ◽  
Privacy Preservation ◽  
Fine Tuning ◽  
Quantization Scheme ◽  
Raw Data ◽  
Resource Limited ◽  
Lower Accuracy ◽  
Bandwidth Consumption

The emerging edge-cloud collaborative Deep Learning (DL) paradigm aims at improving the performance of practical DL implementations in terms of cloud bandwidth consumption, response latency, and data privacy preservation. Focusing on bandwidth efficient edge-cloud collaborative training of DNN-based classifiers, we present CDC, a Classification Driven Compression framework that reduces bandwidth consumption while preserving classification accuracy of edge-cloud collaborative DL. Specifically, to reduce bandwidth consumption, for resource-limited edge servers, we develop a lightweight autoencoder with a classification guidance for compression with classification driven feature preservation, which allows edges to only upload the latent code of raw data for accurate global training on the Cloud. Additionally, we design an adjustable quantization scheme adaptively pursuing the tradeoff between bandwidth consumption and classification accuracy under different network conditions, where only fine-tuning is required for rapid compression ratio adjustment. Results of extensive experiments demonstrate that, compared with DNN training with raw data, CDC consumes 14.9× less bandwidth with an accuracy loss no more than 1.06%, and compared with DNN training with data compressed by AE without guidance, CDC introduces at least 100% lower accuracy loss.

scholarly journals Learning to Learn Morphological Inflection for Resource-Poor Languages

2020 ◽  
Vol 34 (05) ◽  
pp. 8058-8065
Author(s):  
Katharina Kann ◽  
Samuel R. Bowman ◽  
Kyunghyun Cho
Keyword(s):  
Fine Tuning ◽  
Target Language ◽  
Model Parameters ◽  
Transfer Model ◽  
Absolute Accuracy ◽  
Learning To Learn ◽  
Suggested Approach ◽  
High Resource ◽  
Resource Poor ◽  
Cross Lingual

We propose to cast the task of morphological inflection—mapping a lemma to an indicated inflected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.

scholarly journals Scanning electron microscope fine tuning using four-bar piezoelectric actuated mechanism

2018 ◽  
Vol 69 (1) ◽  
pp. 24-31
Author(s):  
Khaled S. Hatamleh ◽  
Qais A. Khasawneh ◽  
Adnan Al-Ghasem ◽  
Mohammad A. Jaradat ◽  
Laith Sawaqed ◽  
...  
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Inverse Kinematic ◽  
Fine Tuning ◽  
Electron Microscopes ◽  
Tuning Strategy ◽  
Scanning Electron Microscopes ◽  
Fine Tune ◽  
Kinematic Solution ◽  
Scanning Electron

Abstract Scanning Electron Microscopes are extensively used for accurate micro/nano images exploring. Several strategies have been proposed to fine tune those microscopes in the past few years. This work presents a new fine tuning strategy of a scanning electron microscope sample table using four bar piezoelectric actuated mechanisms. The introduced paper presents an algorithm to find all possible inverse kinematics solutions of the proposed mechanism. In addition, another algorithm is presented to search for the optimal inverse kinematic solution. Both algorithms are used simultaneously by means of a simulation study to fine tune a scanning electron microscope sample table through a pre-specified circular or linear path of motion. Results of the study shows that, proposed algorithms were able to minimize the power required to drive the piezoelectric actuated mechanism by a ratio of 97.5% for all simulated paths of motion when compared to general non-optimized solution.

Sign in / Sign up

Export Citation Format

Share Document