Online learning [91 94] is a well-established learning paradigm whose strategy is learning one instance at a time, instead of in an offline or batch learning fashion, which needs to collect the full information of training data.
There are also two learning updates: on-line learning, which updates the network after presenting each exemplar, and batch learning, which updates it after the presentation of the entire training set.
Tissue = Normal and Tumor tissue; Batch = Different batches in which the samples were sequenced.
In situations where new data arrive continually, online learning algorithms are computationally much less costly than batch learning ones in maintaining the model up-to-date.
In the initial training phase, the read-out weights were updated via an online learning or batch learning process, in distinct simulations (see Sect. 4.4 for details).
Previously, we developed a modified SOM (batch-learning SOM: BLSOM), which depends on neither the order of data input nor the initial condition, for codon frequencies in gene sequences and oligonucleotide frequencies in genomic sequences.
By modifying the conventional SOM, we have previously developed Batch-Learning SOM (BLSOM), which allows classification of sequence fragments according to species, solely depending on the oligonucleotide composition.
In this paper, we implement and parallelize batch learning for a Sequence-to-Sequence (Seq2Seq) model, which is the most basic model of NMT, without using a padding strategy.
The performance comparisons between ILRBF-BP and the other batch learning algorithms are shown in Table 2.
The incremental learning algorithm for the hybrid RBF-BP (ILRBF-BP), which is a batch learning algorithm, is proposed by combining the proposed incremental learning algorithm with the hybrid RBF-BP network architecture.
