Recent research in the deep learning field has produced a plethora of new architectures. At the same time, a growing number of groups are applying deep learning to new applications. Some of these groups are likely to be composed of inexperienced deep learning practitioners who are baffled by the dizzying array of architecture choices and therefore opt to use an older architecture (i.e., Alexnet...

Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset [15].We propose a new architecture for the GQ-CNN and describe practical improvements that increase...

This paper describes the participation of the ECOUAN team in the LifeCLEF 2015 challenge. We used a deep learning approach in which the complete system was learned without hand-engineered components. We pre-trained a convolutional neural network using 1.8 million images and used a fine-tuning strategy to transfer learned recognition capabilities from general domains to the specific challenge of...

MR-only radiotherapy treatment planning requires accurate MR-to-CT synthesis. Current deep learning methods for MR-to-CT synthesis depend on pairwise aligned MR and CT training images of the same patient. However, misalignment between paired images could lead to errors in synthesized CT images. To overcome this, we propose to train a generative adversarial network (GAN) with unpaired MR and CT ...

In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both deep learning and linguistic structures, we propose a tree-based convolutional neural network model which exploit various long-distance relationships betwee...

This paper investigates a Deep Learning (DL) approach for image recognition. We have considered two DL neural models: Convolutional Neural Network (CNN) and Deep Belief Network (DBN). We have chosen several architectures for each of the proposed models. We have chosen Caltech101 dataset to train and test the above proposed models; this database is composed by images belonging to 101 widely vari...

09.15 10.45 Paper Session I o Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval Konstantinos Sfikas, Theoharis Theoharis and Ioannis Pratikakis o LightNet: A Lightweight 3D Convolutional Neural Network for Real-Time 3D Object Recognition Shuaifeng Zhi, Yongxiang Liu, Xiang Li and Yulan Guo o Unstructured point cloud semantic labeling using deep...

We review the deep reinforcement learning setting, in which an agent receiving high-dimensional input from an environment learns a control policy without supervision using multilayer neural networks. We then extend the Neural Fitted Q Iteration value-based reinforcement learning algorithm (Riedmiller et al) by introducing a novel variation which we call Regularized Convolutional Neural Fitted Q...