January 29, 2020

3343 words 16 mins read

Paper Group ANR 723

Early warning in egg production curves from commercial hens: A SVM approach. A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration. Understanding Geometry of Encoder-Decoder CNNs. Towards an automatic recognition of mixed languages: The Ukrainian-Russian hybrid language Surzhyk. The Neural State Pushdown Automata. …

Early warning in egg production curves from commercial hens: A SVM approach


Title	Early warning in egg production curves from commercial hens: A SVM approach
Authors	Iván Ramírez Morales, Daniel Rivero Cebrián, Enrique Fernández Blanco, Alejandro Pazos Sierra
Abstract	Artificial Intelligence allows the improvement of our daily life, for instance, speech and handwritten text recognition, real time translation and weather forecasting are common used applications. In the livestock sector, machine learning algorithms have the potential for early detection and warning of problems, which represents a significant milestone in the poultry industry. Production problems generate economic loss that could be avoided by acting in a timely manner. In the current study, training and testing of support vector machines are addressed, for an early detection of problems in the production curve of commercial eggs, using farm’s egg production data of 478,919 laying hens grouped in 24 flocks. Experiments using support vector machines with a 5 k-fold cross-validation were performed at different previous time intervals, to alert with up to 5 days of forecasting interval, whether a flock will experience a problem in production curve. Performance metrics such as accuracy, specificity, sensitivity, and positive predictive value were evaluated, reaching 0-day values of 0.9874, 0.9876, 0.9783 and 0.6518 respectively on unseen data (test-set). The optimal forecasting interval was from zero to three days, performance metrics decreases as the forecasting interval is increased. It should be emphasized that this technique was able to issue an alert a day in advance, achieving an accuracy of 0.9854, a specificity of 0.9865, a sensitivity of 0.9333 and a positive predictive value of 0.6135. This novel application embedded in a computer system of poultry management is able to provide significant improvements in early detection and warning of problems related to the production curve.
Tasks	Weather Forecasting
Published	2019-04-08
URL	http://arxiv.org/abs/1904.03987v1
PDF	http://arxiv.org/pdf/1904.03987v1.pdf
PWC	https://paperswithcode.com/paper/early-warning-in-egg-production-curves-from
Repo
Framework

A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration


Title	A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration
Authors	Riddhish Bhalodia, Shireen Y. Elhabian, Ladislav Kavan, Ross T. Whitaker
Abstract	Spatial transformations are enablers in a variety of medical image analysis applications that entail aligning images to a common coordinate systems. Population analysis of such transformations is expected to capture the underlying image and shape variations, and hence these transformations are required to produce anatomically feasible correspondences. This is usually enforced through some smoothness-based generic regularization on deformation field. Alternatively, population-based regularization has been shown to produce anatomically accurate correspondences in cases where anatomically unaware (i.e., data independent) fail. Recently, deep networks have been for unsupervised image registration, these methods are computationally faster and maintains the accuracy of state of the art methods. However, these networks use smoothness penalty on deformation fields and ignores population-level statistics of the transformations. We propose a novel neural network architecture that simultaneously learns and uses the population-level statistics of the spatial transformations to regularize the neural networks for unsupervised image registration. This regularization is in the form of a bottleneck autoencoder, which encodes the population level information of the deformation fields in a low-dimensional manifold. The proposed architecture produces deformation fields that describe the population-level features and associated correspondences in an anatomically relevant manner and are statistically compact relative to the state-of-the-art approaches while maintaining computational efficiency. We demonstrate the efficacy of the proposed architecture on synthetic data sets, as well as 2D and 3D medical data.
Tasks	Image Registration
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05825v2
PDF	https://arxiv.org/pdf/1908.05825v2.pdf
PWC	https://paperswithcode.com/paper/a-cooperative-autoencoder-for-population
Repo
Framework

Understanding Geometry of Encoder-Decoder CNNs


Title	Understanding Geometry of Encoder-Decoder CNNs
Authors	Jong Chul Ye, Woon Kyoung Sung
Abstract	Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to obtain coherent geometric view why such an architecture gives the desired performance. Inspired by recent theoretical understanding on generalizability, expressivity and optimization landscape of neural networks, as well as the theory of convolutional framelets, here we provide a unified theoretical framework that leads to a better understanding of geometry of encoder-decoder CNNs. Our unified mathematical framework shows that encoder-decoder CNN architecture is closely related to nonlinear basis representation using combinatorial convolution frames, whose expressibility increases exponentially with the network depth. We also demonstrate the importance of skipped connection in terms of expressibility, and optimization landscape.
Tasks
Published	2019-01-22
URL	https://arxiv.org/abs/1901.07647v2
PDF	https://arxiv.org/pdf/1901.07647v2.pdf
PWC	https://paperswithcode.com/paper/understanding-geometry-of-encoder-decoder
Repo
Framework

Towards an automatic recognition of mixed languages: The Ukrainian-Russian hybrid language Surzhyk


Title	Towards an automatic recognition of mixed languages: The Ukrainian-Russian hybrid language Surzhyk
Authors	Nataliya Sira, Giorgio Maria Di Nunzio, Viviana Nosilia
Abstract	Language interference is common in today’s multilingual societies where more languages are being in contact and as a global final result leads to the creation of hybrid languages. These, together with doubts on their right to be officially recognised made emerge in the area of computational linguistics the problem of their automatic identification and further elaboration. In this paper, we propose a first attempt to identify the elements of a Ukrainian-Russian hybrid language, Surzhyk, through the adoption of the example-based rules created with the instruments of programming language R. Our example-based study consists of: 1) analysis of spoken samples of Surzhyk registered by Del Gaudio (2010) in Kyiv area and creation of the written corpus; 2) production of specific rules on the identification of Surzhyk patterns and their implementation; 3) testing the code and analysing the effectiveness.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08582v1
PDF	https://arxiv.org/pdf/1912.08582v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-automatic-recognition-of-mixed
Repo
Framework

The Neural State Pushdown Automata


Title	The Neural State Pushdown Automata
Authors	Ankur Mali, Alexander Ororbia, C. Lee Giles
Abstract	In order to learn complex grammars, recurrent neural networks (RNNs) require sufficient computational resources to ensure correct grammar recognition. A widely-used approach to expand model capacity would be to couple an RNN to an external memory stack. Here, we introduce a “neural state” pushdown automaton (NSPDA), which consists of a digital stack, instead of an analog one, that is coupled to a neural network state machine. We empirically show its effectiveness in recognizing various context-free grammars (CFGs). First, we develop the underlying mechanics of the proposed higher order recurrent network and its manipulation of a stack as well as how to stably program its underlying pushdown automaton (PDA) to achieve desired finite-state network dynamics. Next, we introduce a noise regularization scheme for higher-order (tensor) networks, to our knowledge the first of its kind, and design an algorithm for improved incremental learning. Finally, we design a method for inserting grammar rules into a NSPDA and empirically show that this prior knowledge improves its training convergence time by an order of magnitude and, in some cases, leads to better generalization. The NSPDA is also compared to a classical analog stack neural network pushdown automaton (NNPDA) as well as a wide array of first and second-order RNNs with and without external memory, trained using different learning algorithms. Our results show that, for Dyck(2) languages, prior rule-based knowledge is critical for optimization convergence and for ensuring generalization to longer sequences at test time. We observe that many RNNs with and without memory, but no prior knowledge, fail to converge and generalize poorly on CFGs.
Tasks	Tensor Networks
Published	2019-09-07
URL	https://arxiv.org/abs/1909.05233v2
PDF	https://arxiv.org/pdf/1909.05233v2.pdf
PWC	https://paperswithcode.com/paper/the-neural-state-pushdown-automata
Repo
Framework

A Low Computational Approach for Price Tag Recognition


Title	A Low Computational Approach for Price Tag Recognition
Authors	M. A. Aliev, D. A. Bocharov, I. A. Kunina, D. P. Nikolaev
Abstract	In this work we discuss the task of search, localization and recognition of price zone within a photograph of the price tag. The task is being addressed for the case when image is acquired by small-scale digital camera and calculation device has significant resource constraints. The proposed approach is based on Niblack binarization algorithm, analysis and clasterization of connected components in conditions of known price tag geometrical model. The algorithm was tested on a private dataset and has shown high quality.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01923v1
PDF	https://arxiv.org/pdf/1912.01923v1.pdf
PWC	https://paperswithcode.com/paper/a-low-computational-approach-for-price-tag
Repo
Framework

Machine Learning Phase Transitions with a Quantum Processor


Title	Machine Learning Phase Transitions with a Quantum Processor
Authors	Alexey Uvarov, Andrey Kardashin, Jacob Biamonte
Abstract	Machine learning has emerged as a promising approach to study the properties of many-body systems. Recently proposed as a tool to classify phases of matter, the approach relies on classical simulation methods$-$such as Monte Carlo$-$which are known to experience an exponential slowdown when simulating certain quantum systems. To overcome this slowdown while still leveraging machine learning, we propose a variational quantum algorithm which merges quantum simulation and quantum machine learning to classify phases of matter. Our classifier is directly fed labeled states recovered by the variational quantum eigensolver algorithm, thereby avoiding the data reading slowdown experienced in many applications of quantum enhanced machine learning. We propose families of variational ansatz states that are inspired directly by tensor networks. This allows us to use tools from tensor network theory to explain properties of the phase diagrams the presented method recovers. Finally, we propose a nearest-neighbour (checkerboard) quantum neural network. This majority vote quantum classifier is successfully trained to recognize phases of matter with $99%$ accuracy for the transverse field Ising model and $94%$ accuracy for the XXZ model. These findings suggest that our merger between quantum simulation and quantum enhanced machine learning offers a fertile ground to develop computational insights into quantum systems.
Tasks	Quantum Machine Learning, Tensor Networks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10155v2
PDF	https://arxiv.org/pdf/1906.10155v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-phase-transitions-with-a
Repo
Framework

A New Anchor Word Selection Method for the Separable Topic Discovery


Title	A New Anchor Word Selection Method for the Separable Topic Discovery
Authors	Kun He, Wu Wang, Xiaosen Wang, John E. Hopcroft
Abstract	Separable Non-negative Matrix Factorization (SNMF) is an important method for topic modeling, where “separable” assumes every topic contains at least one anchor word, defined as a word that has non-zero probability only on that topic. SNMF focuses on the word co-occurrence patterns to reveal topics by two steps: anchor word selection and topic recovery. The quality of the anchor words strongly influences the quality of the extracted topics. Existing anchor word selection algorithm is to greedily find an approximate convex hull in a high-dimensional word co-occurrence space. In this work, we propose a new method for the anchor word selection by associating the word co-occurrence probability with the words similarity and assuming that the most different words on semantic are potential candidates for the anchor words. Therefore, if the similarity of a word-pair is very low, then the two words are very likely to be the anchor words. According to the statistical information of text corpora, we can get the similarity of all word-pairs. We build the word similarity graph where the nodes correspond to words and weights on edges stand for the word-pair similarity. Following this way, we design a greedy method to find a minimum edge-weight anchor clique of a given size in the graph for the anchor word selection. Extensive experiments on real-world corpus demonstrate the effectiveness of the proposed anchor word selection method that outperforms the common convex hull-based methods on the revealed topic quality. Meanwhile, our method is much faster than typical SNMF based method.
Tasks
Published	2019-05-10
URL	https://arxiv.org/abs/1905.06109v1
PDF	https://arxiv.org/pdf/1905.06109v1.pdf
PWC	https://paperswithcode.com/paper/190506109
Repo
Framework

Injecting Prior Knowledge for Transfer Learning into Reinforcement Learning Algorithms using Logic Tensor Networks


Title	Injecting Prior Knowledge for Transfer Learning into Reinforcement Learning Algorithms using Logic Tensor Networks
Authors	Samy Badreddine, Michael Spranger
Abstract	Human ability at solving complex tasks is helped by priors on object and event semantics of their environment. This paper investigates the use of similar prior knowledge for transfer learning in Reinforcement Learning agents. In particular, the paper proposes to use a first-order-logic language grounded in deep neural networks to represent facts about objects and their semantics in the real world. Facts are provided as background knowledge a priori to learning a policy for how to act in the world. The priors are injected with the conventional input in a single agent architecture. As proof-of-concept, the paper tests the system in simple experiments that show the importance of symbolic abstraction and flexible fact derivation. The paper shows that the proposed system can learn to take advantage of both the symbolic layer and the image layer in a single decision selection module.
Tasks	Tensor Networks, Transfer Learning
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06576v1
PDF	https://arxiv.org/pdf/1906.06576v1.pdf
PWC	https://paperswithcode.com/paper/injecting-prior-knowledge-for-transfer
Repo
Framework

High Performance Scalable FPGA Accelerator for Deep Neural Networks


Title	High Performance Scalable FPGA Accelerator for Deep Neural Networks
Authors	Sudarshan Srinivasan, Pradeep Janedula, Saurabh Dhoble, Sasikanth Avancha, Dipankar Das, Naveen Mellempudi, Bharat Daga, Martin Langhammer, Gregg Baeckler, Bharat Kaul
Abstract	Low-precision is the first order knob for achieving higher Artificial Intelligence Operations (AI-TOPS). However the algorithmic space for sub-8-bit precision compute is diverse, with disruptive changes happening frequently, making FPGAs a natural choice for Deep Neural Network inference, In this work we present an FPGA-based accelerator for CNN inference acceleration. We use {\it INT-8-2} compute (with {\it 8 bit} activation and {2 bit} weights) which is recently showing promise in the literature, and which no known ASIC, CPU or GPU natively supports today. Using a novel Adaptive Logic Module (ALM) based design, as a departure from traditional DSP based designs, we are able to achieve high performance measurement of 5 AI-TOPS for {\it Arria10} and project a performance of 76 AI-TOPS at 0.7 TOPS/W for {\it Stratix10}. This exceeds known CPU, GPU performance and comes close to best known ASIC (TPU) numbers, while retaining the versatility of the FPGA platform for other applications.
Tasks
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11809v1
PDF	https://arxiv.org/pdf/1908.11809v1.pdf
PWC	https://paperswithcode.com/paper/high-performance-scalable-fpga-accelerator
Repo
Framework

Semantic Change and Emerging Tropes In a Large Corpus of New High German Poetry


Title	Semantic Change and Emerging Tropes In a Large Corpus of New High German Poetry
Authors	Thomas Haider, Steffen Eger
Abstract	Due to its semantic succinctness and novelty of expression, poetry is a great test bed for semantic change analysis. However, so far there is a scarcity of large diachronic corpora. Here, we provide a large corpus of German poetry which consists of about 75k poems with more than 11 million tokens, with poems ranging from the 16th to early 20th century. We then track semantic change in this corpus by investigating the rise of tropes (`love is magic’) over time and detecting change points of meaning, which we find to occur particularly within the German Romantic period. Additionally, through self-similarity, we reconstruct literary periods and find evidence that the law of linear semantic change also applies to poetry. \|
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12136v1
PDF	https://arxiv.org/pdf/1909.12136v1.pdf
PWC	https://paperswithcode.com/paper/semantic-change-and-emerging-tropes-in-a-1
Repo
Framework

CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting


Title	CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting
Authors	Sarkar Snigdha Sarathi Das, Syed Md. Mukit Rashid, Mohammed Eunus Ali
Abstract	Crowd counting problem that counts the number of people in an image has been extensively studied in recent years. In this paper, we introduce a new variant of crowd counting problem, namely “Categorized Crowd Counting”, that counts the number of people sitting and standing in a given image. Categorized crowd counting has many real-world applications such as crowd monitoring, customer service, and resource management. The major challenges in categorized crowd counting come from high occlusion, perspective distortion and the seemingly identical upper body posture of sitting and standing persons. Existing density map based approaches perform well to approximate a large crowd, but lose important local information necessary for categorization. On the other hand, traditional detection-based approaches perform poorly in occluded environments, especially when the crowd size gets bigger. Hence, to solve the categorized crowd counting problem, we develop a novel attention-based deep learning framework that addresses the above limitations. In particular, our approach works in three phases: i) We first generate basic detection based sitting and standing density maps to capture the local information; ii) Then, we generate a crowd counting based density map as global counting feature; iii) Finally, we have a cross-branch segregating refinement phase that splits the crowd density map into final sitting and standing density maps using attention mechanism. Extensive experiments show the efficacy of our approach in solving the categorized crowd counting problem.
Tasks	Crowd Counting
Published	2019-12-12
URL	https://arxiv.org/abs/1912.05765v1
PDF	https://arxiv.org/pdf/1912.05765v1.pdf
PWC	https://paperswithcode.com/paper/cccnet-an-attention-based-deep-learning
Repo
Framework

Skeleton-based Action Recognition of People Handling Objects


Title	Skeleton-based Action Recognition of People Handling Objects
Authors	Sunoh Kim, Kimin Yun, Jongyoul Park, Jin Young Choi
Abstract	In visual surveillance systems, it is necessary to recognize the behavior of people handling objects such as a phone, a cup, or a plastic bag. In this paper, to address this problem, we propose a new framework for recognizing object-related human actions by graph convolutional networks using human and object poses. In this framework, we construct skeletal graphs of reliable human poses by selectively sampling the informative frames in a video, which include human joints with high confidence scores obtained in pose estimation. The skeletal graphs generated from the sampled frames represent human poses related to the object position in both the spatial and temporal domains, and these graphs are used as inputs to the graph convolutional networks. Through experiments over an open benchmark and our own data sets, we verify the validity of our framework in that our method outperforms the state-of-the-art method for skeleton-based action recognition.
Tasks	Action Recognition In Videos, Pose Estimation, Skeleton Based Action Recognition, Temporal Action Localization
Published	2019-01-21
URL	http://arxiv.org/abs/1901.06882v1
PDF	http://arxiv.org/pdf/1901.06882v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-action-recognition-of-people
Repo
Framework

Word and character segmentation directly in run-length compressed handwritten document images


Title	Word and character segmentation directly in run-length compressed handwritten document images
Authors	Amarnath R, P. Nagabhushan, Mohammed Javed
Abstract	From the literature, it is demonstrated that performing text-line segmentation directly in the run-length compressed handwritten document images significantly reduces the computational time and memory space. In this paper, we investigate the issues of word and character segmentation directly on the run-length compressed document images. Primarily, the spreads of the characters are intelligently extracted from the foreground runs of the compressed data and subsequently connected components are established. The spacing between the connected components would be larger between the adjacent words when compared to that of intra-words. With this knowledge, a threshold is empirically chosen for inter-word separation. Every connected component within a word is further analysed for character segmentation. Here, min-cut graph concept is used for separating the touching characters. Over-segmentation and under-segmentation issues are addressed by insertion and deletion operations respectively. The approach has been developed particularly for compressed handwritten English document images. However, the model has been tested on non-English document images.
Tasks
Published	2019-08-18
URL	https://arxiv.org/abs/1909.05146v1
PDF	https://arxiv.org/pdf/1909.05146v1.pdf
PWC	https://paperswithcode.com/paper/word-and-character-segmentation-directly-in
Repo
Framework

Learning to Segment Skin Lesions from Noisy Annotations


Title	Learning to Segment Skin Lesions from Noisy Annotations
Authors	Zahra Mirikharaji, Yiqi Yan, Ghassan Hamarneh
Abstract	Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption of deep networks. In the task of medical image segmentation, requiring pixel-level semantic annotations performed by human experts exacerbate this difficulty. This paper proposes a new framework to train a fully convolutional segmentation network from a large set of cheap unreliable annotations and a small set of expert-level clean annotations. We propose a spatially adaptive reweighting approach to treat clean and noisy pixel-level annotations commensurately in the loss function. We deploy a meta-learning approach to assign higher importance to pixels whose loss gradient direction is closer to those of clean data. Our experiments on training the network using segmentation ground truth corrupted with different levels of annotation noise show how spatial reweighting improves the robustness of deep networks to noisy annotations.
Tasks	Medical Image Segmentation, Meta-Learning, Semantic Segmentation
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03815v2
PDF	https://arxiv.org/pdf/1906.03815v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-segment-skin-lesions-from-noisy
Repo
Framework