Overcoming small minirhizotron datasets using transfer learning
نویسندگان
چکیده
منابع مشابه
Overcoming data scarcity with transfer learning
Despite increasing focus on data publication and discovery in materials science and related fields, the global view of materials data is highly sparse. This sparsity encourages training models on the union of multiple datasets, but simple unions can prove problematic as (ostensibly) equivalent properties may be measured or computed differently depending on the data source. These hidden contextu...
متن کاملLearning using Large Datasets
This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for the case of small-scale and large-scale learning problems. Small-scale learning problems are subject to the usual approximation– estimation tradeoff. Large-scale learning problems are subject to a qualitatively differ...
متن کاملLearning Singly-Recursive Relations from Small Datasets
The inductive logic programming system LOPSTER was created to demonstrate the advantage of basing induction on logical implication rather than -subsumption. LOPSTER's sub-uni cation procedures allow it to induce recursive relations using a minimum number of examples, whereas inductive logic programming algorithms based on -subsumption require many more examples to solve induction tasks. However...
متن کاملMeasuring root turnover using the minirhizotron technique
Cheng, W.-X., Coleman, D.C. and Box, J.E., Jr., 1991. Measuring root turnover using the minirhizo° tron technique. Agric. Ecosystems Environ., 34: 261-267. Measurement of root turnover has been one of the most difficult problems in terrestrial ecosystem studies owing to the lack of an appropriate method. In this paper, a method for measuring intraseasonal root turnover is described. The recentl...
متن کاملA Transfer Learning Approach for Applying Matrix Factorization to Small ITS Datasets
Machine Learning methods for Performance Prediction in Intelligent Tutoring Systems (ITS) have proven their efficacy; specific methods, e.g. Matrix Factorization (MF), however suffer from the lack of available information about new tasks or new students. In this paper we show how this problem could be solved by applying Transfer Learning (TL), i.e. combining similar but not equal datasets to tr...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computers and Electronics in Agriculture
سال: 2020
ISSN: 0168-1699
DOI: 10.1016/j.compag.2020.105466