Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition Joseph Lin Chu Artificial neural networks have been widely used for machine learning tasks such as object recognition. Recent developments have made use of biologically inspired architectures, such as the Convolutional Neural Network, and the Deep Belief Network. A the...

For the purpose of automatically evaluating speakers’ humor usage, we build a presentation corpus containing humorous utterances based on TED talks. Compared to previous data resources supporting humor recognition research, ours has several advantages, including (a) both positive and negative instances coming from a homogeneous data set, (b) containing a large number of speakers, and (c) being ...

Human beings are visual animals; the eyes are the most compact structure of all the sensory organs, and the visual intelligence of the human brain is rich in content. Exercise, behaviour, and thinking activities use visual sensory data as their greatest source of information. The more flexible and talented we become, the more we rely on visual intelligence. What general business and decision ma...

The objective of this work is to find objects in paintings by learning object-category classifiers from available sources of natural images. Finding such objects is of much benefit to the art history community as well as being a challenging problem in large-scale retrieval and domain adaptation. We make the following contributions: (i) we show that object classifiers, learnt using Convolutional...

Protein-ligand scoring is an important step in a structure-based drug design pipeline. Selecting a correct binding pose and predicting the binding affinity of a protein-ligand complex enables effective virtual screening. Machine learning techniques can make use of the increasing amounts of structural data that are becoming publicly available. Convolutional neural network (CNN) scoring functions...

Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp d...

We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively studied and different heuristics have been proposed to construct a low rank basis of the filters after training. In this work, we train flattened networks that ...

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding, for example for recognition on mobile platforms or in embedded systems. In this paper we propose C...

Combining Convolutional Neural Networks and Word Sentiment Sequence Features for Chinese Text Sentiment Classification Zhao Chen1, Ruifeng Xu1, Lin Gui1, Qin Lu2 (1. School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong, 518000, China; 2. Depart of Computing, The Hong Kong Polytechnic University, Hong Kong, China) Abstract: Recen...

Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is consistent with CNNs with random weights. We give an exact connection to a par...