[PDF][PDF] Accelerating t-SNE using tree-based algorithms
L Van Der Maaten - The journal of machine learning research, 2014 - jmlr.org
The paper investigates the acceleration of t-SNE—an embedding technique that is
commonly used for the visualization of high-dimensional data in scatter plots—using two …
commonly used for the visualization of high-dimensional data in scatter plots—using two …
Salicon: Saliency in context
Saliency in Context (SALICON) is an ongoing effort that aims at understanding and
predicting visual attention. This paper presents a new method to collect large-scale human …
predicting visual attention. This paper presents a new method to collect large-scale human …
Interleaved group convolutions
In this paper, we present a simple and modularized neural network architecture, named
interleaved group convolutional neural networks (IGCNets). The main point lies in a novel …
interleaved group convolutional neural networks (IGCNets). The main point lies in a novel …
Do deep nets really need to be deep?
Currently, deep neural networks are the state of the art on problems such as speech
recognition and computer vision. In this paper we empirically demonstrate that shallow feed …
recognition and computer vision. In this paper we empirically demonstrate that shallow feed …
A survey of research on cloud robotics and automation
The Cloud infrastructure and its extensive set of Internet-accessible resources has potential
to provide significant benefits to robots and automation systems. We consider robots and …
to provide significant benefits to robots and automation systems. We consider robots and …
Big data deep learning: challenges and perspectives
XW Chen, X Lin - IEEE access, 2014 - ieeexplore.ieee.org
Deep learning is currently an extremely active research area in machine learning and
pattern recognition society. It has gained huge successes in a broad area of applications …
pattern recognition society. It has gained huge successes in a broad area of applications …
Scalable nearest neighbor algorithms for high dimensional data
For many computer vision and machine learning problems, large training sets are key for
good performance. However, the most computationally expensive part of many computer …
good performance. However, the most computationally expensive part of many computer …
Places: An image database for deep scene understanding
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning
algorithms to reach near-human semantic classification at tasks such as object and scene …
algorithms to reach near-human semantic classification at tasks such as object and scene …
Learning to hash for indexing big data—A survey
The explosive growth in Big Data has attracted much attention in designing efficient indexing
and search methods recently. In many critical applications such as large-scale search and …
and search methods recently. In many critical applications such as large-scale search and …
How big data will change accounting
JD Warren, KC Moffitt, P Byrnes - Accounting horizons, 2015 - publications.aaahq.org
Big Data will have increasingly important implications for accounting, even as new types of
data become accessible. The video, audio, and textual information made available via Big …
data become accessible. The video, audio, and textual information made available via Big …