In this article, we discuss the Grothendieck group completion (GGC) of a gyrogroup. Consequently, we show that there is a one to one correspondence between actions and representations of a gyrogroup, and actions and representations of its Grothendiec
k group completion. We also introduce the concept of an action of a right gyrogroup.
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video. In this paper, we take visual understanding to a higher level where systems are challenged to answer questions that involve
mentally simulating the hypothetical consequences of performing specific actions in a given scenario. Towards that end, we formulate a vision-language question answering task based on the CLEVR (Johnson et. al., 2017) dataset. We then modify the best existing VQA methods and propose baseline solvers for this task. Finally, we motivate the development of better vision-language models by providing insights about the capability of diverse architectures to perform joint reasoning over image-text modality. Our dataset setup scripts and codes will be made publicly available at https://github.com/shailaja183/clevr_hyp.
Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search. In this work, we explore the use of scene graphs for solving the VQA task.
We conduct experiments on the GQA dataset which presents a challenging set of questions requiring counting, compositionality and advanced reasoning capability, and provides scene graphs for a large number of images. We adopt image + question architectures for use with scene graphs, evaluate various scene graph generation techniques for unseen images, propose a training curriculum to leverage human-annotated and auto-generated scene graphs, and build late fusion architectures to learn from multiple image representations. We present a multi-faceted study into the use of scene graphs for VQA, making this work the first of its kind.
This work examines the problem of exact data interpolation via sparse (neuron count), infinitely wide, single hidden layer neural networks with leaky rectified linear unit activations. Using the atomic norm framework of [Chandrasekaran et al., 2012],
we derive simple characterizations of the convex hulls of the corresponding atomic sets for this problem under several different constraints on the weights and biases of the network, thus obtaining equivalent convex formulations for these problems. A modest extension of our proposed framework to a binary classification problem is also presented. We explore the efficacy of the resulting formulations experimentally, and compare with networks trained via gradient descent.
This paper proposes the implementation of programmable threshold logic gate (TLG) crossbar array based on modified TLG cells for high speed processing and computation. The proposed TLG array operation does not depend on input signal and time pulses,
comparing to the existing architectures. The circuit is implemented using TSMC $180nm$ CMOS technology. The on-chip area and power dissipation of the simulated $3times 4$ TLG array is $1463 mu m^2$ and $425 mu W$, respectively.
This paper presents the new approach in implementation of analog-to-digital converter (ADC) that is based on Hopfield neural-network architecture. Hopfield neural ADC (NADC) is a type of recurrent neural network that is effective in solving simple op
timization problems, such as analog-to-digital conversion. The main idea behind the proposed design is to use multiple 2-bit Hopfield NADCs operating as quantizers in parallel, where analog input signal to each successive 2-bit Hopfield ADC block is passed through a voltage level shifter. This is followed by a neural network encoder to remove the quantization errors. In traditional Hopfield NADC based designs, increasing the number of bits could require proper scaling of the network parameters, in particular digital output operating region. Furthermore, the resolution improvement of traditional Hopfield NADC creates digital error that increases with the increasing number of bits. The proposed design is scalable in number of bits and number of quantization levels, and can maintain the magnitude of digital output code within a manageable operating voltage range.
In the last decade we have observed a mass increase of information, in particular information that is shared through smartphones. Consequently, the amount of information that is available does not allow the average user to be aware of all his options
. In this context, recommender systems use a number of techniques to help a user find the desired product. Hence, nowadays recommender systems play an important role. Recommender Systems aim to identify products that best fits user preferences. These techniques are advantageous to both users and vendors, as it enables the user to rapidly find what he needs and the vendors to promote their products and sales. As the industry became aware of the gains that could be accomplished by using these algorithms, also a very interesting problem for many researchers, recommender systems became a very active area since the mid 90s. Having in mind that this is an ongoing problem the present thesis intends to observe the value of using a recommender algorithm to find users likes by observing her domain preferences. In a balanced probabilistic method, this thesis will show how news topics can be used to recommend news articles. In this thesis, we used different machine learning methods to determine the user ratings for an article. To tackle this problem, supervised learning methods such as linear regression, Naive Bayes and logistic regression are used. All the aforementioned models have a different nature which has an impact on the solution of the given problem. Furthermore, number of experiments are presented and discussed to identify the feature set that fits best to the problem.
Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The first part
of the survey details the various datasets for VQA and compares them along some common factors. The second part of this survey details the different approaches for VQA, classified into four types: non-deep learning models, deep learning models without attention, deep learning models with attention, and other models which do not fit into the first three. Finally, we compare the performances of these approaches and provide some directions for future work.
We examine the Si(111) multi-valley quantum Hall system and show that it exhibits an exceptionally rich interplay of broken symmetries and quantum Hall ordering already near integer fillings $ u$ in the range $ u=0-6$. This six-valley system has a la
rge $[SU(2)]^3rtimes D_3$ symmetry in the limit where the magnetic length is much larger than the lattice constant. We find that the discrete ${D}_3$ factor breaks over a broad range of fillings at a finite temperature transition to a discrete nematic phase. As $T rightarrow 0$ the $[SU(2)]^3$ continuous symmetry also breaks: completely near $ u =3$, to a residual $[U(1)]^2times SU(2)$ near $ u=2$ and $4$ and to a residual $U(1)times [SU(2)]^2$ near $ u=1$ and $5$. Interestingly, the symmetry breaking near $ u=2,4$ and $ u=3$ involves a combination of selection by thermal fluctuations known as order by disorder and a selection by the energetics of Skyrme lattices induced by moving away from the commensurate fillings, a mechanism we term order by doping. We also exhibit modestly simpler analogs in the four-valley Si(110) system.
