We present a transductive learning algorithm that takes as input training examples from a distribution P and arbitrary (unlabeled) test examples, possibly chosen by an adversary. This is unlike prior work that assumes...
详细信息
Scratches are a common phenomenon in the production of the PET bottle preform, and traditional inspection by human eyes bring troubles to the automatic production process. In this paper, deep learning algorithm was us...
详细信息
During the learning process, the evaluation of learners’ products becomes difficult with immense number of students in universities, and it can be a heavy task for a teacher in such complicated subjects, for this pur...
详细信息
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situ...
详细信息
An important research direction in machine learning has centered around developing meta-learning algorithms to tackle few-shot learning. An especially successful algorithm has been Model Agnostic Meta-learning (MAML),...
详细信息
Extreme learning machine (ELM) is an effective classification and prediction learning algorithm based on feedforward neural network (FNN). This paper presents the Phasmatodea (stick insect) population evolution algori...
详细信息
Gene expressions profiling empowers many biological studies in various fields by comprehensive characterization of cellular status under different experimental conditions. Despite the recent advances in high-throughpu...
详细信息
ISBN:
(纸本)9783030452568
Gene expressions profiling empowers many biological studies in various fields by comprehensive characterization of cellular status under different experimental conditions. Despite the recent advances in high-throughput technologies, profiling the whole-genome set is still challenging and expensive. Based on the fact that there is high correlation among the expression patterns of different genes, the above issue can be addressed by a cost-effective approach that collects only a small subset of genes, called landmark genes, as the representative of the entire genome set and estimates the remaining ones, called target genes, via the computational model. Several shallow and deep regression models have been presented in the literature for inferring the expressions of target genes. However, the shallow models suffer from underfitting due to their insufficient capacity in capturing the complex nature of gene expression data, and the existing deep models are prone to overfitting due to the lack of using the interrelations of target genes in the learning framework. To address these challenges, we formulate the gene expression inference as a multi-task learning problem and propose a novel deep multi-task learning algorithm with automatically learning the biological interrelations among target genes and utilizing such information to enhance the prediction. In particular, we employ a multi-layer sub-network with low dimensional latent variables for learning the interrelations among target genes (i.e. distinct predictive tasks), and impose a seamless and easy to implement regularization on deep models. Unlike the conventional complicated multi-task learning methods, which can only deal with tens or hundreds of tasks, our proposed algorithm can effectively learn the interrelations from the large-scale ($$\sim $$10,000) tasks on the gene expression inference problem, and does not suffer from cost-prohibitive operations. Experimental results indicate the superiority of our method c
The challenges in current WiFi based gait recognition models, such as the limited classification ability, high storage cost, long training time and restricted deployment on hardware platforms, motivate us to propose a...
详细信息
To keep in pace with ever-increasing customer demands, providing instant and useful responses is a prominent need of service providers. Latest technical developments have led to the advent of a faster, easier solution...
详细信息
Text classification is the task of forming semantic groups of text documents by assigning predefined class labels. It has wide range of real-life applications in various domains such as engineering, medical science, l...
详细信息
暂无评论