Deep learning multidimensional projections
نویسندگان
چکیده
منابع مشابه
Demystifying Deep Learning: A Geometric Approach to Iterative Projections
Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We s...
متن کاملProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
Deep neural networks have become ubiquitous for applications related to visual recognition and language understanding tasks. However, it is often prohibitive to use typical neural network models on devices like mobile phones or smart watches since the model sizes are huge and cannot fit in the limited memory available on such devices. While these devices could make use of machine learning model...
متن کاملHessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks
Multidimensional recurrent neural networks (MDRNNs) have shown a remarkable performance in the area of speech and handwriting recognition. The performance of an MDRNN is improved by further increasing its depth, and the difficulty of learning the deeper network is overcome by using Hessian-free (HF) optimization. Given that connectionist temporal classification (CTC) is utilized as an objective...
متن کاملAttribute-based Visual Explanation of Multidimensional Projections
Multidimensional projections (MPs) are key tools for the analysis of multidimensional data. MPs reduce data dimensionality while keeping the original distance structure in the low-dimensional output space, typically shown by a 2D scatterplot. While MP techniques grow more precise and scalable, they still do not show how the original dimensions (attributes) influence the projection’s layout. In ...
متن کاملExplaining Neighborhood Preservation for Multidimensional Projections
Dimensionality reduction techniques are the tools of choice for exploring high-dimensional datasets by means of low-dimensional projections. However, even state-of-the-art projection methods fail, up to various degrees, in perfectly preserving the structure of the data, expressed in terms of inter-point distances and point neighborhoods. To support better interpretation of a projection, we prop...
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: Information Visualization
سال: 2020
ISSN: 1473-8716,1473-8724
DOI: 10.1177/1473871620909485