"high level feature" is a correct and usable phrase in written English.
It is commonly used in technical or academic writing to describe a feature that is fundamental or important in a particular context. For example: - The high level features of this computer program include advanced algorithms and a user-friendly interface. - The high level features of this job include a competitive salary and opportunities for career growth. - In terms of design, the high level features of this building are its striking facade and sustainable materials. - The high level features of this camera make it a top choice for professional photographers. - The high level features of this car model include a powerful engine and advanced safety features.
In this work, we investigated the performance of three popular methods for matrix decomposition: Principal Component Analysis (PCA), Non-negative Matrix Factorization (NMF) and Sparse Coding (SC) as unsupervised high level feature extractors for the self-taught learning algorithm.
In this study, we investigated the performance of several matrix decomposition methods, such as PCA, NMF and sparse coding when applied for high level feature extraction in the self-taught learning algorithm with respect to the music genre classification task.
Mearns et al. [26] employed counterpoint as a high level feature from musical theory background to classify the style of musical pieces based on a symbolic representation of the score (Kern Format).
First, this is a rather late available, high level feature of characters, making it a more difficult and time consuming selection criterion than for instance spatial frequency or color [40], [41].
Once all features were extracted, death certificates were transformed from original terms to vectors of features (one vector per certificate); for example, each word (TokenStem) or SNOMED CT concept represented a single feature dimension in the vector, with features grouped into high level feature types (TokenStem or SCTConceptId).
The domain knowledge pre-labels the task space into different regions and builds a connection between the direct sensory experience and the high level features.
Visual saliency is modelled as a combination of low level, as well as high level features which become important at the higher-level visual cortex.
We also explore different combinations of observation and transition feature functions based on the learned high level features from convolution part.
The proposed fully convolutional CNN architecture, called uResNet, that comprised an analysis path, that gradually learns low and high level features, followed by a synthesis path, that gradually combines and up-samples the low and high level features into a class likelihood semantic segmentation.
Using the coarse-grained community prior, we can get high level features of the nodes' categories.
Deep Neural Networks have many layers allowing them to extract high level features from the raw data.
