scholarly journals Deep Bucket Elimination

2021 ◽  
Author(s):  
Yasaman Razeghi ◽  
Kalev Kask ◽  
Yadong Lu ◽  
Pierre Baldi ◽  
Sakshi Agarwal ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Partition Function ◽  
Graphical Models ◽  
State Of The Art ◽  
Proof Of Concept ◽  
Accurate Approximation ◽  
Current State

Bucket Elimination (BE) is a universal inference scheme that can solve most tasks over probabilistic and deterministic graphical models exactly. However, it often requires exponentially high levels of memory (in the induced-width) preventing its execution. In the spirit of exploiting Deep Learning for inference tasks, in this paper, we will use neural networks to approximate BE. The resulting Deep Bucket Elimination (DBE) algorithm is developed for computing the partition function. We provide a proof-of-concept empirically using instances from several different benchmarks, showing that DBE can be a more accurate approximation than current state-of-the-art approaches for approximating BE (e.g. the mini-bucket schemes), especially when problems are sufficiently hard.

scholarly journals Training a neural network to learn other dimensionality reduction removes data size restrictions in bioinformatics and provides a new route to exploring data representations

2020 ◽  
Author(s):  
Alex Dexter ◽  
Spencer A. Thomas ◽  
Rory T. Steven ◽  
Kenneth N. Robinson ◽  
Adam J. Taylor ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Dimensionality Reduction ◽  
Computational Analysis ◽  
New Technologies ◽  
State Of The Art ◽  
Current State ◽  
Data Representations ◽  
Non Linear ◽  
Linear Dimensionality Reduction

AbstractHigh dimensionality omics and hyperspectral imaging datasets present difficult challenges for feature extraction and data mining due to huge numbers of features that cannot be simultaneously examined. The sample numbers and variables of these methods are constantly growing as new technologies are developed, and computational analysis needs to evolve to keep up with growing demand. Current state of the art algorithms can handle some routine datasets but struggle when datasets grow above a certain size. We present a training deep learning via neural networks on non-linear dimensionality reduction, in particular t-distributed stochastic neighbour embedding (t-SNE), to overcome prior limitations of these methods.One Sentence SummaryAnalysis of prohibitively large datasets by combining deep learning via neural networks with non-linear dimensionality reduction.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

scholarly journals Using Convolutional Neural Networks to Map Houses Suitable for Electric Vehicle Home Charging

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 135-149
Author(s):  
James Flynn ◽  
Cinzia Giannetti
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Urban Areas ◽  
Proof Of Concept ◽  
Major Step ◽  
Dominant Form ◽  
Residential Properties ◽  
The Uk ◽  
Ev Charging ◽  
Unique Dataset

With Electric Vehicles (EV) emerging as the dominant form of green transport in the UK, it is critical that we better understand existing infrastructures in place to support the uptake of these vehicles. In this multi-disciplinary paper, we demonstrate a novel end-to-end workflow using deep learning to perform automated surveys of urban areas to identify residential properties suitable for EV charging. A unique dataset comprised of open source Google Street View images was used to train and compare three deep neural networks and represents the first attempt to classify residential driveways from streetscape imagery. We demonstrate the full system workflow on two urban areas and achieve accuracies of 87.2% and 89.3% respectively. This proof of concept demonstrates a promising new application of deep learning in the field of remote sensing, geospatial analysis, and urban planning, as well as a major step towards fully autonomous artificially intelligent surveying techniques of the built environment.

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals A Survey of Graphical Page Object Detection with Deep Neural Networks

2021 ◽  
Author(s):  
Jwalin Bhatt ◽  
Khurram Azeem Hashmi ◽  
Muhammad Zeshan Afzal ◽  
Didier Stricker
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Conceptual Understanding ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Learning Approaches ◽  
Document Images ◽  
Essential Information ◽  
Current State ◽  
High Level

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

scholarly journals A Robust Context-Based Deep Learning Approach for Highly Imbalanced Hyperspectral Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Juan F. Ramirez Rochac ◽  
Nian Zhang ◽  
Lara A. Thompson ◽  
Tolessa Deksissa
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Mineral Exploration ◽  
Classification Models ◽  
Noise Resistance ◽  
Deep Convolutional Neural Networks ◽  
Current State ◽  
Feature Augmentation ◽  
Active Research ◽  
Hyperspectral Classification

Hyperspectral imaging is an area of active research with many applications in remote sensing, mineral exploration, and environmental monitoring. Deep learning and, in particular, convolution-based approaches are the current state-of-the-art classification models. However, in the presence of noisy hyperspectral datasets, these deep convolutional neural networks underperform. In this paper, we proposed a feature augmentation approach to increase noise resistance in imbalanced hyperspectral classification. Our method calculates context-based features, and it uses a deep convolutional neuronet (DCN). We tested our proposed approach on the Pavia datasets and compared three models, DCN, PCA + DCN, and our context-based DCN, using the original datasets and the datasets plus noise. Our experimental results show that DCN and PCA + DCN perform well on the original datasets but not on the noisy datasets. Our robust context-based DCN was able to outperform others in the presence of noise and was able to maintain a comparable classification accuracy on clean hyperspectral images.

scholarly journals Soft Threshold Ternary Networks

2020 ◽  
Author(s):  
Weixiang Xu ◽  
Xiangyu He ◽  
Tianli Zhao ◽  
Qinghao Hu ◽  
Peisong Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Mobile Devices ◽  
State Of The Art ◽  
Performance Gap ◽  
Training Time ◽  
Current State ◽  
The Arts ◽  
Soft Threshold ◽  
And Storage ◽  
Selection Of

Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary values. In previous ternarized neural networks, a hard threshold Δ is introduced to determine quantization intervals. Although the selection of Δ greatly affects the training results, previous works estimate Δ via an approximation or treat it as a hyper-parameter, which is suboptimal. In this paper, we present the Soft Threshold Ternary Networks (STTN), which enables the model to automatically determine quantization intervals instead of depending on a hard threshold. Concretely, we replace the original ternary kernel with the addition of two binary kernels at training time, where ternary values are determined by the combination of two corresponding binary values. At inference time, we add up the two binary kernels to obtain a single ternary kernel. Our method dramatically outperforms current state-of-the-arts, lowering the performance gap between full-precision networks and extreme low bit networks. Experiments on ImageNet with AlexNet (Top-1 55.6%), ResNet-18 (Top-1 66.2%) achieves new state-of-the-art.

scholarly journals AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays

2021 ◽  
Vol 7 ◽  
pp. e495
Author(s):  
Saleh Albahli ◽  
Hafiz Tayyab Rauf ◽  
Abdulelah Algosaibi ◽  
Valentina Emilia Balas
Keyword(s):  
Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Synthetic Data ◽  
X Rays ◽  
Deep Convolutional Neural Networks ◽  
Current State ◽  
Pathology Classification ◽  
Wide Range ◽  
Multi Class Classification

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect and diagnose a wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches and have produced impressive chest-related clinical outcomes, specific techniques may not contribute many advantages if one type of disease is detected without the rest being identified. Those who tried to identify multiple chest-related diseases were ineffective due to insufficient data and the available data not being balanced. This research provides a significant contribution to the healthcare industry and the research community by proposing a synthetic data augmentation in three deep Convolutional Neural Networks (CNNs) architectures for the detection of 14 chest-related diseases. The employed models are DenseNet121, InceptionResNetV2, and ResNet152V2; after training and validation, an average ROC-AUC score of 0.80 was obtained competitive as compared to the previous models that were trained for multi-class classification to detect anomalies in x-ray images. This research illustrates how the proposed model practices state-of-the-art deep neural networks to classify 14 chest-related diseases with better accuracy.

scholarly journals Detecting Emotions in English and Arabic Tweets

Information ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 98 ◽  
Author(s):  
Tariq Ahmad ◽  
Allan Ramsay ◽  
Hanady Ahmed
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Learning Algorithms ◽  
General Purpose ◽  
Machine Learning Algorithms ◽  
Current State ◽  
Optimal Thresholds ◽  
Alternative Approach

Assigning sentiment labels to documents is, at first sight, a standard multi-label classification task. Many approaches have been used for this task, but the current state-of-the-art solutions use deep neural networks (DNNs). As such, it seems likely that standard machine learning algorithms, such as these, will provide an effective approach. We describe an alternative approach, involving the use of probabilities to construct a weighted lexicon of sentiment terms, then modifying the lexicon and calculating optimal thresholds for each class. We show that this approach outperforms the use of DNNs and other standard algorithms. We believe that DNNs are not a universal panacea and that paying attention to the nature of the data that you are trying to learn from can be more important than trying out ever more powerful general purpose machine learning algorithms.

scholarly journals PPDIST, global 0.1° daily and 3-hourly precipitation probability distribution climatologies for 1979–2018

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Hylke E. Beck ◽  
Seth Westra ◽  
Jackson Tan ◽  
Florian Pappenberger ◽  
George J. Huffman ◽  
...  
Keyword(s):  
Neural Networks ◽  
Probability Distribution ◽  
State Of The Art ◽  
Intertropical Convergence Zone ◽  
Coefficient Of Determination ◽  
Current State ◽  
Peak Intensity ◽  
Global Land ◽  
The Neural Networks ◽  
Better Than

Abstract We introduce the Precipitation Probability DISTribution (PPDIST) dataset, a collection of global high-resolution (0.1°) observation-based climatologies (1979–2018) of the occurrence and peak intensity of precipitation (P) at daily and 3-hourly time-scales. The climatologies were produced using neural networks trained with daily P observations from 93,138 gauges and hourly P observations (resampled to 3-hourly) from 11,881 gauges worldwide. Mean validation coefficient of determination (R2) values ranged from 0.76 to 0.80 for the daily P occurrence indices, and from 0.44 to 0.84 for the daily peak P intensity indices. The neural networks performed significantly better than current state-of-the-art reanalysis (ERA5) and satellite (IMERG) products for all P indices. Using a 0.1 mm 3 h−1 threshold, P was estimated to occur 12.2%, 7.4%, and 14.3% of the time, on average, over the global, land, and ocean domains, respectively. The highest P intensities were found over parts of Central America, India, and Southeast Asia, along the western equatorial coast of Africa, and in the intertropical convergence zone. The PPDIST dataset is available via www.gloh2o.org/ppdist.

Sign in / Sign up

Export Citation Format

Share Document