Heterogeneous transfer learning techniques for machine learning

Iqbal, Muhammad; Luo, Bin; Khan, Tamoor; Mehmood, Rashid; Sadiq, Muhammad

doi:10.1007/s42044-017-0004-z

Cited by 12 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer Learning In Transfer Learning, one tries to transfer knowledge of previous tasks to new, unseen tasks (Pan and Yang 2009; Taylor and Stone 2009), which can be challenging when a new task comes from a different distribution than the one used for training Iqbal et al (2018). The distinction between Transfer Learning and Meta-Learning has become more opaque over time.…”

Section: Contrast With Other Fieldsmentioning

confidence: 99%

A survey of deep meta-learning

Huisman¹,

Rijn²,

Plaat³

2021

Artif Intell Rev

228

View full text Add to dashboard Cite

Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field of Deep Meta-Learning advances at great speed, but lacks a unified, in-depth overview of current techniques. With this work, we aim to bridge this gap. After providing the reader with a theoretical foundation, we investigate and summarize key methods, which are categorized into (i) metric-, (ii) model-, and (iii) optimization-based techniques. In addition, we identify the main open challenges, such as performance evaluations on heterogeneous benchmarks, and reduction of the computational costs of meta-learning.

show abstract

Section: Contrast With Other Fieldsmentioning

confidence: 99%

A survey of deep meta-learning

Huisman¹,

Rijn²,

Plaat³

2021

Artif Intell Rev

228

View full text Add to dashboard Cite

show abstract

“…The growth estimation of education institutions by linear regression model is discussed by Iqbal and Luo (2019). Iqbal et al (2018) discussed the relationship between heterogeneous transmission learning and other methods of machine learning. Ahmed et al (2016) explore climatic conditions and their effects on fruit trees near roadsides show different productivity in the dusty climate in Miyyaghundi (Quetta) and Ghanjdori (Mastung), Pakistan.…”

Section: Introductionmentioning

confidence: 99%

Effect of climate change on fruit by co-integration and machine learning

Khan

Qiu

Banjar

et al. 2021

IJCCSM

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this paper is to assess the impacts on production of five fruit crops from 1961 to 2018 of energy use, CO2 emissions, farming areas and the labor force in China. Design/methodology/approach This analysis applied the autoregressive distributed lag-bound testing (ARDL) approach, Granger causality method and Johansen co-integration test to predict long-term co-integration and relation between variables. Four machine learning methods are used for prediction of the accuracy of climate effect on fruit production. Findings The Johansen test findings have shown that the fruit crop growth, energy use, CO2 emissions, harvested land and labor force have a long-term co-integration relation. The outcome of the long-term use of CO2 emission and rural population has a negative influence on fruit crops. The energy consumption, harvested area, total fruit yield and agriculture labor force have a positive influence on six fruit crops. The long-run relationships reveal that a 1% increase in rural population and CO2 will decrease fruit crop production by −0.59 and −1.97. The energy consumption, fruit harvested area, total fruit yield and agriculture labor force will increase fruit crop production by 0.17%, 1.52%, 1.80% and 4.33%, respectively. Furthermore, uni-directional causality is correlated with the growth of fruit crops and energy consumption. Also, the results indicate that the bi-directional causality impact varies from CO2 emissions to agricultural areas to fruit crops. Originality/value This study also fills the literature gap in implementing ARDL for agricultural fruits of China, used machine learning methods to examine the impact of climate change and to explore this important issue.

show abstract

“…To extract useful components of software from existing software data a technique called Data Mining is used. It acts as a bridge between software repository and the knowledge required 2 . Using different techniques patterns are analyzed to make concrete decisions.…”

Section: Introductionmentioning

confidence: 99%

“…It acts as a bridge between software repository and the knowledge required. 2 Using different techniques patterns are analyzed to make concrete decisions. For decision-making Machine Learning comes into light.…”

Section: Introductionmentioning

confidence: 99%

Software reuse analytics using integrated random forest and gradient boosting machine learning algorithm

Sandhu

Batth

2020

Softw Pract Exp

View full text Add to dashboard Cite

The term Cleaner Production (CP) for Production Companies is contemplated as influential to get sustainable production. CP mainly deals with three R's that is, reuse, reduce, and recycle. For software enterprise, the software reuse plays a pivotal role. Software reuse is a process of producing new products or software from the existing software by updating it. To extract useful information from the existing software data mining comes into light. The algorithms used for software reuse face issues related to maintenance cost, accuracy, and performance. Also, the currently used algorithm does not give accurate results on whether the component of software can be reused. Machine Learning gives the best results to predicate if the given software component is reusable or not. This paper introduces an integrated Random Forest and Gradient Boosting Machine Learning Algorithm (RFGBM) which test the reusability of the given software code considering the object‐oriented parameters such as cohesion, coupling, cyclomatic complexity, bugs, number of children, and depth inheritance tree. Further, the proposed algorithm is compared with J48, AdaBoostM1, LogitBoost, Part, One R, LMT, JRip, DecisionStump algorithms. Performance metrices like accuracy, error rate, Relative Absolute Error, and Mean Absolute Error are improved using RFGBM. This algorithm also utilizes data preprocessing with the help of an unsupervised filter to remove the missing value for efficiency improvement. Proposed algorithm outperforms existing in term of performance parameters.

show abstract

Heterogeneous transfer learning techniques for machine learning

Cited by 12 publications

References 32 publications

A survey of deep meta-learning

A survey of deep meta-learning

Effect of climate change on fruit by co-integration and machine learning

Software reuse analytics using integrated random forest and gradient boosting machine learning algorithm

Contact Info

Product

Resources

About