scholarly journals A Meta-Learning Approach for Custom Model Training

2019 ◽  
Vol 33 ◽  
pp. 9937-9938
Author(s):  
Amir Erfan Eshratifar ◽  
Mohammad Saeed Abrishami ◽  
David Eigen ◽  
Massoud Pedram
Keyword(s):  
Transfer Learning ◽  
Large Data ◽  
Learning Approaches ◽  
Target Task ◽  
Training Approach ◽  
Starting Point ◽  
Meta Learning ◽  
Future Task ◽  
Model Training ◽  
Training Examples

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pretrained starting point. But as we experimentally show, metalearning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In this paper, we propose a joint training approach that combines both transfer-learning and meta-learning. Benefiting from the advantages of each, our method obtains improved generalization performance on unseen target tasks in both few- and many-class and few- and many-shot scenarios.

scholarly journals Effective Training of Deep Convolutional Neural Networks for Hyperspectral Image Classification through Artificial Labeling

2020 ◽  
Vol 12 (16) ◽  
pp. 2653 ◽  
Author(s):  
Wojciech Masarczyk ◽  
Przemysław Głomb ◽  
Bartosz Grabowski ◽  
Mateusz Ostaszewski
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Network Architecture ◽  
Hyperspectral Image ◽  
Large Data ◽  
Learning Approaches ◽  
Classification Problems ◽  
Deep Convolutional Neural Networks ◽  
Additional Advantage ◽  
Hyperspectral Classification

Hyperspectral imaging is a rich source of data, allowing for a multitude of effective applications. However, such imaging remains challenging because of large data dimension and, typically, a small pool of available training examples. While deep learning approaches have been shown to be successful in providing effective classification solutions, especially for high dimensional problems, unfortunately they work best with a lot of labelled examples available. The transfer learning approach can be used to alleviate the second requirement for a particular dataset: first the network is pre-trained on some dataset with large amount of training labels available, then the actual dataset is used to fine-tune the network. This strategy is not straightforward to apply with hyperspectral images, as it is often the case that only one particular image of some type or characteristic is available. In this paper, we propose and investigate a simple and effective strategy of transfer learning that uses unsupervised pre-training step without label information. This approach can be applied to many of the hyperspectral classification problems. The performed experiments show that it is very effective at improving the classification accuracy without being restricted to a particular image type or neural network architecture. The experiments were carried out on several deep neural network architectures and various sizes of labeled training sets. The greatest improvement in overall accuracy on the Indian Pines and Pavia University datasets is over 21 and 13 percentage points, respectively. An additional advantage of the proposed approach is the unsupervised nature of the pre-training step, which can be done immediately after image acquisition, without the need of the potentially costly expert’s time.

scholarly journals Transfer Learning in Breast Cancer Diagnoses via Ultrasound Imaging

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 738
Author(s):  
Gelan Ayana ◽  
Kokeb Dese ◽  
Se-woon Choe
Keyword(s):  
Breast Cancer ◽  
Transfer Learning ◽  
Learning Approaches ◽  
Target Domain ◽  
Training Models ◽  
Large Numbers ◽  
Breast Image ◽  
Learning Techniques ◽  
Starting Point ◽  
Machine Learning Approach

Transfer learning is a machine learning approach that reuses a learning method developed for a task as the starting point for a model on a target task. The goal of transfer learning is to improve performance of target learners by transferring the knowledge contained in other (but related) source domains. As a result, the need for large numbers of target-domain data is lowered for constructing target learners. Due to this immense property, transfer learning techniques are frequently used in ultrasound breast cancer image analyses. In this review, we focus on transfer learning methods applied on ultrasound breast image classification and detection from the perspective of transfer learning approaches, pre-processing, pre-training models, and convolutional neural network (CNN) models. Finally, comparison of different works is carried out, and challenges—as well as outlooks—are discussed.

scholarly journals Transfer Learning for Synthetic Examples Selection in Meta-learning

2018 ◽  
Author(s):  
Regina R. Parente ◽  
Ricardo B. C. Prudencio
Keyword(s):  
Transfer Learning ◽  
Computational Cost ◽  
Learning Performance ◽  
Combining Data ◽  
Meta Learning ◽  
Training Examples ◽  
One Class Classification ◽  
Good Set ◽  
High Computational Cost ◽  
Selection Of

In Meta-learning, training examples are generated from experiments performed with a pool of candidate algorithms in a number of problems (real or synthetic). Generating a good set of examples can be difficult due to the low availability of real datasets in some domains and the high computational cost of labeling. In this paper, we focus on the selection of training meta-examples by combining data manipulation and Transfer Learning via One-class classification. So, the most relevant examples are selected to be labeled. Our experiments revealed that it is possible to reduce the computational cost of generating meta- examples and maintain the meta-learning performance.

scholarly journals Plankton classification with high-throughput submersible holographic microscopy and transfer learning

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Liam MacNeil ◽  
Sergey Missan ◽  
Junliang Luo ◽  
Thomas Trappenberg ◽  
Julie LaRoche
Keyword(s):  
Transfer Learning ◽  
High Throughput ◽  
Quantitative Imaging ◽  
Optical Resolution ◽  
Image Features ◽  
In Situ Monitoring ◽  
Decision Threshold ◽  
Learning Approaches ◽  
Recent Developments ◽  
Model Training

Abstract Background Plankton are foundational to marine food webs and an important feature for characterizing ocean health. Recent developments in quantitative imaging devices provide in-flow high-throughput sampling from bulk volumes—opening new ecological challenges exploring microbial eukaryotic variation and diversity, alongside technical hurdles to automate classification from large datasets. However, a limited number of deployable imaging instruments have been coupled with the most prominent classification algorithms—effectively limiting the extraction of curated observations from field deployments. Holography offers relatively simple coherent microscopy designs with non-intrusive 3-D image information, and rapid frame rates that support data-driven plankton imaging tasks. Classification benchmarks across different domains have been set with transfer learning approaches, focused on repurposing pre-trained, state-of-the-art deep learning models as classifiers to learn new image features without protracted model training times. Combining the data production of holography, digital image processing, and computer vision could improve in-situ monitoring of plankton communities and contribute to sampling the diversity of microbial eukaryotes. Results Here we use a light and portable digital in-line holographic microscope (The HoloSea) with maximum optical resolution of 1.5 μm, intensity-based object detection through a volume, and four different pre-trained convolutional neural networks to classify > 3800 micro-mesoplankton (> 20 μm) images across 19 classes. The maximum classifier performance was quickly achieved for each convolutional neural network during training and reached F1-scores > 89%. Taking classification further, we show that off-the-shelf classifiers perform strongly across every decision threshold for ranking a majority of the plankton classes. Conclusion These results show compelling baselines for classifying holographic plankton images, both rare and plentiful, including several dinoflagellate and diatom groups. These results also support a broader potential for deployable holographic microscopes to sample diverse microbial eukaryotic communities, and its use for high-throughput plankton monitoring.

scholarly journals PhaLP: A Database for the Study of Phage Lytic Proteins and Their Evolution

Viruses ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1240
Author(s):  
Bjorn Criel ◽  
Steff Taelman ◽  
Wim Van Criekinge ◽  
Michiel Stock ◽  
Yves Briers
Keyword(s):  
Protein Sequence ◽  
Early Research ◽  
Learning Approaches ◽  
Specific Design ◽  
Starting Point ◽  
Community Of Researchers ◽  
The Rich ◽  
Rich Content ◽  
Broad Community ◽  
High Diversity

Phage lytic proteins are a clinically advanced class of novel enzyme-based antibiotics, so-called enzybiotics. A growing community of researchers develops phage lytic proteins with the perspective of their use as enzybiotics. A successful translation of enzybiotics to the market requires well-considered selections of phage lytic proteins in early research stages. Here, we introduce PhaLP, a database of phage lytic proteins, which serves as an open portal to facilitate the development of phage lytic proteins. PhaLP is a comprehensive, easily accessible and automatically updated database (currently 16,095 entries). Capitalizing on the rich content of PhaLP, we have mapped the high diversity of natural phage lytic proteins and conducted analyses at three levels to gain insight in their host-specific evolution. First, we provide an overview of the modular diversity. Secondly, datamining and interpretable machine learning approaches were adopted to reveal host-specific design rules for domain architectures in endolysins. Lastly, the evolution of phage lytic proteins on the protein sequence level was explored, revealing host-specific clusters. In sum, PhaLP can act as a starting point for the broad community of enzybiotic researchers, while the steadily improving evolutionary insights will serve as a natural inspiration for protein engineers.

Auto-sharing parameters for transfer learning based on multi-objective optimization

2021 ◽  
pp. 1-13
Author(s):  
Hailin Liu ◽  
Fangqing Gu ◽  
Zixian Lin
Keyword(s):  
Transfer Learning ◽  
Optimization Problem ◽  
Data Sets ◽  
Multi Objective Optimization ◽  
Particle Swarm Optimizer ◽  
Real World Data ◽  
Data Set ◽  
Target Task ◽  
Main Research ◽  
Multi Objective

Transfer learning methods exploit similarities between different datasets to improve the performance of the target task by transferring knowledge from source tasks to the target task. “What to transfer” is a main research issue in transfer learning. The existing transfer learning method generally needs to acquire the shared parameters by integrating human knowledge. However, in many real applications, an understanding of which parameters can be shared is unknown beforehand. Transfer learning model is essentially a special multi-objective optimization problem. Consequently, this paper proposes a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization and solves the optimization problem by using a multi-swarm particle swarm optimizer. Each task objective is simultaneously optimized by a sub-swarm. The current best particle from the sub-swarm of the target task is used to guide the search of particles of the source tasks and vice versa. The target task and source task are jointly solved by sharing the information of the best particle, which works as an inductive bias. Experiments are carried out to evaluate the proposed algorithm on several synthetic data sets and two real-world data sets of a school data set and a landmine data set, which show that the proposed algorithm is effective.

Analysis of Meta-Learning Approaches for TCGA Pan-cancer Datasets

2020 ◽  
Author(s):  
Jingyuan Chou ◽  
Stefan Bekiranov ◽  
Chongzhi Zang ◽  
Mengdi Huai ◽  
Aidong Zhang
Keyword(s):  
Learning Approaches ◽  
Meta Learning ◽  
Pan Cancer

scholarly journals Reinforcement Learning Approaches in Social Robotics

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1292
Author(s):  
Neziha Akalin ◽  
Amy Loutfi
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Social Robotics ◽  
Research Field ◽  
Social Robots ◽  
Learning Approaches ◽  
Reward Function ◽  
Optimal Behavior ◽  
Learning Challenges ◽  
Starting Point

This article surveys reinforcement learning approaches in social robotics. Reinforcement learning is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both reinforcement learning and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. We present a thorough analysis of reinforcement learning approaches in social robotics. In addition to a survey, we categorize existent reinforcement learning approaches based on the used method and the design of the reward mechanisms. Moreover, since communication capability is a prominent feature of social robots, we discuss and group the papers based on the communication medium used for reward formulation. Considering the importance of designing the reward function, we also provide a categorization of the papers based on the nature of the reward. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view of real-world reinforcement learning challenges and proposed solutions, the points that remain to be explored, including the approaches that have thus far received less attention is also given in the paper. Thus, this paper aims to become a starting point for researchers interested in using and applying reinforcement learning methods in this particular research field.

Sign in / Sign up

Export Citation Format

Share Document