Active Learning to Speed-Up the Training Process for Dialogue Act Labelling

2014 ◽  
pp. 253-263
Author(s):  
Fabrizio Ghigi ◽  
Carlos-D. Martínez-Hinarejos ◽  
José-Miguel Benedí
Keyword(s):  
Active Learning ◽  
Training Process ◽  
Speed Up

scholarly journals Classifying streaming data using grammar-based immune programming

2021 ◽  
Author(s):  
Jaspreet Kaur Bassan
Keyword(s):  
Active Learning ◽  
Artificial Immune System ◽  
Streaming Data ◽  
Benchmark Problems ◽  
Artificial Immune ◽  
Training Process ◽  
Real World Data ◽  
Learning Technique ◽  
Computationally Expensive ◽  
Immune Programming

This work proposes a technique for classifying unlabelled streaming data using grammar-based immune programming, a hybrid meta-heuristic where the space of grammar generated solutions is searched by an artificial immune system inspired algorithm. Data is labelled using an active learning technique and is buffered until the system trains adequately on the labelled data. The system is employed in static and in streaming data environments, and is tested and evaluated using synthetic and real-world data. The performances of the system employed in different data settings are compared with each other and with two benchmark problems. The proposed classification system adapted well to the changing nature of streaming data and the active learning technique made the process less computationally expensive by retaining only those instances which favoured the training process.

Optimasi Akurasi Metode Convolutional Neural Network untuk Identifikasi Jenis Sampah

2021 ◽  
Vol 5 (2) ◽  
pp. 312-318
Author(s):  
Rima Dias Ramadhani ◽  
Afandi Nur Aziz Thohari ◽  
Condro Kartiko ◽  
Apri Junaidi ◽  
Tri Ginanjar Laksana ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computer Science ◽  
No Value ◽  
Convolutional Neural Networks ◽  
Training Process ◽  
Indonesian Government ◽  
Speed Up ◽  
Model Training

Waste is goods / materials that have no value in the scope of production, where in some cases the waste is disposed of carelessly and can damage the environment. The Indonesian government in 2019 recorded waste reaching 66-67 million tons, which is higher than the previous year, which was 64 million tons. Waste is differentiated based on its type, namely organic and anorganic waste. In the field of computer science, the process of sensing the type waste can be done using a camera and the Convolutional Neural Networks (CNN) method, which is a type of neural network that works by receiving input in the form of images. The input will be trained using CNN architecture so that it will produce output that can recognize the object being inputted. This study optimizes the use of the CNN method to obtain accurate results in identifying types of waste. Optimization is done by adding several hyperparameters to the CNN architecture. By adding hyperparameters, the accuracy value is 91.2%. Meanwhile, if the hyperparameter is not used, the accuracy value is only 67.6%. There are three hyperparameters used to increase the accuracy value of the model. They are dropout, padding, and stride. 20% increase in dropout to increase training overfit. Whereas padding and stride are used to speed up the model training process.

scholarly journals G2Basy: A framework to improve the RNN language model and ease overfitting problem

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249820
Author(s):  
Lu Yuwen ◽  
Shuyu Chen ◽  
Xiaohan Yuan
Keyword(s):  
Language Model ◽  
Word Embedding ◽  
Language Models ◽  
Batch Size ◽  
Training Process ◽  
Improve Performance ◽  
Step Size ◽  
Learning Rates ◽  
Speed Up ◽  
Overfitting Problem

Recurrent neural networks are efficient ways of training language models, and various RNN networks have been proposed to improve performance. However, with the increase of network scales, the overfitting problem becomes more urgent. In this paper, we propose a framework—G2Basy—to speed up the training process and ease the overfitting problem. Instead of using predefined hyperparameters, we devise a gradient increasing and decreasing technique that changes the parameters training batch size and input dropout simultaneously by a user-defined step size. Together with a pretrained word embedding initialization procedure and the introduction of different optimizers at different learning rates, our framework speeds up the training process dramatically and improves performance compared with a benchmark model of the same scale. For the word embedding initialization, we propose the concept of “artificial features” to describe the characteristics of the obtained word embeddings. We experiment on two of the most often used corpora—the Penn Treebank and WikiText-2 datasets—and both outperform the benchmark results and show potential towards further improvement. Furthermore, our framework shows better results with the larger and more complicated WikiText-2 corpus than with the Penn Treebank. Compared with other state-of-the-art results, we achieve comparable results with network scales hundreds of times smaller and within fewer training epochs.

scholarly journals Fish Detection Using Deep Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Suxia Cui ◽  
Yu Zhou ◽  
Yonghui Wang ◽  
Lujun Zhai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Data Augmentation ◽  
Autonomous Underwater Vehicle ◽  
Training Data ◽  
Training Process ◽  
Data Set ◽  
Speed Up ◽  
Fish Detection ◽  
Process Speed

Recently, human being’s curiosity has been expanded from the land to the sky and the sea. Besides sending people to explore the ocean and outer space, robots are designed for some tasks dangerous for living creatures. Take the ocean exploration for an example. There are many projects or competitions on the design of Autonomous Underwater Vehicle (AUV) which attracted many interests. Authors of this article have learned the necessity of platform upgrade from a previous AUV design project, and would like to share the experience of one task extension in the area of fish detection. Because most of the embedded systems have been improved by fast growing computing and sensing technologies, which makes them possible to incorporate more and more complicated algorithms. In an AUV, after acquiring surrounding information from sensors, how to perceive and analyse corresponding information for better judgement is one of the challenges. The processing procedure can mimic human being’s learning routines. An advanced system with more computing power can facilitate deep learning feature, which exploit many neural network algorithms to simulate human brains. In this paper, a convolutional neural network (CNN) based fish detection method was proposed. The training data set was collected from the Gulf of Mexico by a digital camera. To fit into this unique need, three optimization approaches were applied to the CNN: data augmentation, network simplification, and training process speed up. Data augmentation transformation provided more learning samples; the network was simplified to accommodate the artificial neural network; the training process speed up is introduced to make the training process more time efficient. Experimental results showed that the proposed model is promising, and has the potential to be extended to other underwear objects.

scholarly journals Crop and Weed Classication Using Pixel-wise Segmentation on Ground and Aerial Images

2020 ◽  
Vol 2 (1) ◽  
pp. 39-57
Author(s):  
Mulham Fawakherji
Keyword(s):  
Weed Control ◽  
Near Infrared ◽  
Aerial Images ◽  
Limited Resources ◽  
Infrared Images ◽  
Plant Type ◽  
Training Process ◽  
Mechanical Removal ◽  
Speed Up ◽  
Chemical Inputs

Articial Intelligence (AI) is a key tool in agriculture for implementing sus- tainable strategies for weed control. In traditional weed control, the agro-chemical inputs are uniformly applied to the eld, while innovative approaches using AI aim at minimizing the usage of chemical inputs thanks to local applications. In this paper, we focus on agricultural robotics systems that address the weeding problem by means of selective spraying or mechanical removal of the detected weeds. We present a set of deep learning based methods designed to enable a robot to eciently perform an accurate weed/crop classication from RGB or RGB+NIR (Near Infrared) images. In particular, we use two Convolutional Neural Networks (CNNs) to simplify and speed up the training process. A rst encoder-decoder segmentation network is designed to perform a "plant-type ag- nostic" segmentation between vegetation and soil. Each plant is hence classied between crop and weeds by using a second network, depending on the type of pipeline, for patch-level or pixel-level classication. We introduce also a third CNN, specically designed for setups with limited resources, like in small UAVs (Unmanned Aerial Vehicles), that exploits the proposed encoder-decoder seg- mentation network to eciently estimate crop/weeds local statistics. Quantita- tive experimental results, obtained using multiple publicly available datasets, demonstrate the eectiveness of the proposed approaches.

scholarly journals Classifying streaming data using grammar-based immune programming

2021 ◽  
Author(s):  
Jaspreet Kaur Bassan
Keyword(s):  
Active Learning ◽  
Artificial Immune System ◽  
Streaming Data ◽  
Benchmark Problems ◽  
Artificial Immune ◽  
Training Process ◽  
Real World Data ◽  
Learning Technique ◽  
Computationally Expensive ◽  
Immune Programming

This work proposes a technique for classifying unlabelled streaming data using grammar-based immune programming, a hybrid meta-heuristic where the space of grammar generated solutions is searched by an artificial immune system inspired algorithm. Data is labelled using an active learning technique and is buffered until the system trains adequately on the labelled data. The system is employed in static and in streaming data environments, and is tested and evaluated using synthetic and real-world data. The performances of the system employed in different data settings are compared with each other and with two benchmark problems. The proposed classification system adapted well to the changing nature of streaming data and the active learning technique made the process less computationally expensive by retaining only those instances which favoured the training process.

scholarly journals An On-the-fly Approach to Construct Generalized Energy-Based Fragmentation Machine Learning Force Fields of Complex Systems

2020 ◽  
Author(s):  
zheng cheng ◽  
Zhao Dongbo ◽  
Jing Ma ◽  
Wei Li ◽  
Shuhua Li
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Active Learning ◽  
Potential Energy ◽  
Potential Energy Surface ◽  
Force Field ◽  
Ab Initio Calculation ◽  
Energy Surface ◽  
Speed Up ◽  
Ab Inito

The paper describes a modification to the generalized energy-based fragmentation (GEBF) method that uses a machine fitted potential energy surface for the subsytems instead of ab initio calculation, in order to speed up the calculations. An on-the-fly active learning is used to construct vaious kind of subsystems force field automatically. Our method can bpyss over 99% of the QM calculations during the ab inito molecular dynamics.

scholarly journals METHODS FOR STIMULATION OF ACTIVE LEARNING IN STUDENTS

2019 ◽  
Vol 30 (2) ◽  
pp. 339-344
Author(s):  
Iskra Petkova
Keyword(s):  
Health Care ◽  
Active Learning ◽  
Relative Rate ◽  
Training Methods ◽  
Main Question ◽  
Social Activities ◽  
Pedagogical Practice ◽  
Training Process ◽  
Medical College ◽  
Medical University

In pedagogical practice as a whole there is a growing tendency of employing methods and means that stimulate and activate students to learn during the training process and to enhance their cognitive and professional competencies. An empiric study has been conducted, to discuss and analyze the level of assessment made by students, on methods for active learning stimulation. A survey has been conducted among students studying in two professional orientations. An assessment card has been developed, with main question “Lecturers stimulate active learning of students by using predominantly the following training methods”, structured in two main parts: a) assessment of methods used by the lecturers in the process of training (from 2 to 6 ascending index scale); b) lecturers create conditions for active learning of students by providing opportunity for students to ask questions; give freedom for sharing own ratiocinations; use multimedia devices; include examples from practice; relate the problem to students’ future profession; use various means and techniques (three-index responsive scale: 1 – never, 2 – sometimes, 3 – always). Scope of survey - 102 students from the Medical college at the Medical University of Pleven, from two departments - Health Care (N = 45) and Social Activities (N=57) who have participated voluntarily. The data from the survey for the first part of the question have been analyzed for each department and for the second part the total results from the survey among students from both professional orientations have been shown. Relative rate of highest index responses only are displayed in tables, as they use the highest index and show most determined, explicit choice. The three units subject to analysis, with highest rate of assessment of training methods employed by lecturers, marked by the respondents from Health Care Department are: Seminars -77,78%, Laboratory and Practice - 76,56%, Lectures - 62,22%; results for respondents from Social Activities Department: Case Solving - 68,42%; Lecture, Game Method, Situational Method - 66,68%; Project Method - 56,14%. Regarding the methods for activation of students attitude during the training process the first three places of highest absolute rate of units of analysis, the respondents determine “opportunity for students to ask questions”- 85,29%; “freedom for sharing own ratiocinations” - 82,35%; “using multimedia devices” - 79,41%. The employed methods of training define the main frame for the learning process and support the subject-subjective pedagogical interactions between lecturers and students, for achieving specific educational objects and stimulation the activity in mastering professional knowledge, for creation of a real relation between training and practice. In the training process the lecturers stimulate students’ active attitude by creating conditions for searching answers to various issues, for free expression of opinions and self-development of future specialists.

scholarly journals Fast likelihood-free cosmology with neural density estimators and active learning

2019 ◽  
Author(s):  
Justin Alsing ◽  
Tom Charnock ◽  
Stephen Feeney ◽  
Benjamin Wandelt
Keyword(s):  
Active Learning ◽  
Density Estimation ◽  
Likelihood Function ◽  
Simulated Data ◽  
High Fidelity ◽  
Posterior Inference ◽  
Simulation Based ◽  
Speed Up ◽  
Approximate Bayesian ◽  
Density Estimators

Abstract Likelihood-free inference provides a framework for performing rigorous Bayesian inference using only forward simulations, properly accounting for all physical and observational effects that can be successfully included in the simulations. The key challenge for likelihood-free applications in cosmology, where simulation is typically expensive, is developing methods that can achieve high-fidelity posterior inference with as few simulations as possible. Density-estimation likelihood-free inference (DELFI) methods turn inference into a density estimation task on a set of simulated data-parameter pairs, and give orders of magnitude improvements over traditional Approximate Bayesian Computation approaches to likelihood-free inference. In this paper we use neural density estimators (NDEs) to learn the likelihood function from a set of simulated datasets, with active learning to adaptively acquire simulations in the most relevant regions of parameter space on-the-fly. We demonstrate the approach on a number of cosmological case studies, showing that for typical problems high-fidelity posterior inference can be achieved with just $\mathcal {O}(10^3)$ simulations or fewer. In addition to enabling efficient simulation-based inference, for simple problems where the form of the likelihood is known, DELFI offers a fast alternative to MCMC sampling, giving orders of magnitude speed-up in some cases. Finally, we introduce pydelfi – a flexible public implementation of DELFI with NDEs and active learning – available at https://github.com/justinalsing/pydelfi.

Sign in / Sign up

Export Citation Format

Share Document