Multi-domain Conversation Quality Evaluation via User Satisfaction Estimation. (arXiv:1911.08567v1 [cs.LG])

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and employ annotation schemes with limited generalizability to conversations spanning multiple domains. To address…

Representation Learning with Multisets. (arXiv:1911.08577v1 [cs.LG])

We study the problem of learning permutation invariant representations that can capture “flexible” notions of containment. We formalize this problem via a measure theoretic definition of multisets, and obtain a theoretically-motivated learning model. We propose training this model on a novel task: predicting the size of the symmetric difference (or intersection) between pairs of multisets.…

A Configuration-Space Decomposition Scheme for Learning-based Collision Checking. (arXiv:1911.08581v1 [cs.RO])

Motion planning for robots of high degrees-of-freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space C as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in C. In this paper, we…

Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks. (arXiv:1911.08585v1 [q-bio.NC])

In the past few years, deep learning has transformed artificial intelligence research and led to impressive performance in various difficult tasks. However, it is still unclear how the brain can perform credit assignment across many areas as efficiently as backpropagation does in deep neural networks. In this paper, we introduce a model that relies on…

Solving machine learning optimization problems using quantum computers. (arXiv:1911.08587v1 [quant-ph])

Classical optimization algorithms in machine learning often take a long time to compute when applied to a multi-dimensional problem and require a huge amount of CPU and GPU resource. Quantum parallelism has a potential to speed up machine learning algorithms. We describe a generic mathematical model to leverage quantum parallelism to speed-up machine learning algorithms.…

Unsupervised Bayesian Ising Approximation for revealing the neural dictionary in songbirds. (arXiv:1911.08509v1 [q-bio.QM])

The problem of deciphering how low-level patterns (action potentials in the brain, amino acids in a protein, etc.) drive high-level biological features (sensorimotor behavior, enzymatic function) represents the central challenge of quantitative biology. The lack of general methods for doing so from the size of datasets that can be collected experimentally severely limits our understanding…

Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction. (arXiv:1911.08483v1 [eess.IV])

Gliomas are the most common malignant brain tumourswith intrinsic heterogeneity. Accurate segmentation of gliomas and theirsub-regions on multi-parametric magnetic resonance images (mpMRI)is of great clinical importance, which defines tumour size, shape andappearance and provides abundant information for preoperative diag-nosis, treatment planning and survival prediction. Recent developmentson deep learning have significantly improved the performance of auto-mated…

Modern Antennas and Microwave Circuits — A complete master-level course. (arXiv:1911.08484v1 [eess.SP])

Modern antenna systems include passive antenna structures, passive microwave circuits and interconnections to electronics. Therefore, the antenna engineer should have a deep understanding of antenna theory and should be able to apply microwave engineering concepts. This textbook provides all relevant material for Master-level courses in the domain of antenna systems. The book includes comprehensive material…

Action Recognition Using Volumetric Motion Representations. (arXiv:1911.08511v1 [cs.CV])

Traditional action recognition models are constructed around the paradigm of 2D perspective imagery. Though sophisticated time-series models have pushed the field forward, much of the information is still not exploited by confining the domain to 2D. In this work, we introduce a novel representation of motion as a voxelized 3D vector field and demonstrate how…