scholarly journals Self-supervised Network Evolution for Few-shot Classification

2021 ◽  
Author(s):  
Xuwen Tang ◽  
Zhu Teng ◽  
Baopeng Zhang ◽  
Jianping Fan
Keyword(s):  
Dual Task ◽  
State Of The Art ◽  
Network Evolution ◽  
Label Propagation ◽  
The Novel ◽  
Large Margin ◽  
Second Best ◽  
Shot Classification ◽  
Latent Distribution ◽  
Evolution Approach

Few-shot classification aims to recognize new classes by learning reliable models from very few available samples. It could be very challenging when there is no intersection between the alreadyknown classes (base set) and the novel set (new classes). To alleviate this problem, we propose to evolve the network (for the base set) via label propagation and self-supervision to shrink the distribution difference between the base set and the novel set. Our network evolution approach transfers the latent distribution from the already-known classes to the unknown (novel) classes by: (a) label propagation of the novel/new classes (novel set); and (b) design of dual-task to exploit a discriminative representation to effectively diminish the overfitting on the base set and enhance the generalization ability on the novel set. We conduct comprehensive experiments to examine our network evolution approach against numerous state-of-the-art ones, especially in a higher way setup and cross-dataset scenarios. Notably, our approach outperforms the second best state-of-the-art method by a large margin of 3.25% for one-shot evaluation over miniImageNet.

Multi-Resolution Autoregressive Graph-to-Graph Translation for Molecules

2019 ◽  
Author(s):  
Wengong Jin ◽  
Regina Barzilay ◽  
Tommi S Jaakkola
Keyword(s):  
Drug Discovery ◽  
State Of The Art ◽  
Molecular Graph ◽  
Biochemical Properties ◽  
Large Margin ◽  
Previous State ◽  
Translation Methods ◽  
Atom Level ◽  
Precursor Molecules ◽  
Prior State

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving trees over substructures with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the process of resolving its connectivity to the emerging molecule. We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines by a large margin.

scholarly journals Plant-Based Alternatives to Yogurt: State-of-the-Art and Perspectives of New Biotechnological Challenges

Foods ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 316
Author(s):  
Marco Montemurro ◽  
Erica Pontonio ◽  
Rossana Coda ◽  
Carlo Giuseppe Rizzello
Keyword(s):  
Lactic Acid ◽  
Lactic Acid Bacteria ◽  
State Of The Art ◽  
Protein Digestibility ◽  
The Novel ◽  
Sensory Features ◽  
Long Time ◽  
Biotechnological Processes ◽  
Nutritional Compounds ◽  
Increasing Demand

Due to the increasing demand for milk alternatives, related to both health and ethical needs, plant-based yogurt-like products have been widely explored in recent years. With the main goal to obtain snacks similar to the conventional yogurt in terms of textural and sensory properties and ability to host viable lactic acid bacteria for a long-time storage, several plant-derived ingredients (e.g., cereals, pseudocereals, legumes, and fruits) as well as technological solutions (e.g., enzymatic and thermal treatments) have been investigated. The central role of fermentation in yogurt-like production led to specific selections of lactic acid bacteria strains to be used as starters to guarantee optimal textural (e.g., through the synthesis of exo-polysaccharydes), nutritional (high protein digestibility and low content of anti-nutritional compounds), and functional (synthesis of bioactive compounds) features of the products. This review provides an overview of the novel insights on fermented yogurt-like products. The state-of-the-art on the use of unconventional ingredients, traditional and innovative biotechnological processes, and the effects of fermentation on the textural, nutritional, functional, and sensory features, and the shelf life are described. The supplementation of prebiotics and probiotics and the related health effects are also reviewed.

scholarly journals Meta-Transfer Learning Driven Tensor-Shot Detector for the Autonomous Localization and Recognition of Concealed Baggage Threats

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6450
Author(s):  
Taimur Hassan ◽  
Muhammad Shafay ◽  
Samet Akçay ◽  
Salman Khan ◽  
Mohammed Bennamoun ◽  
...  
Keyword(s):  
Transfer Learning ◽  
State Of The Art ◽  
Autonomous Systems ◽  
Aviation Security ◽  
Dual Energy ◽  
Average Precision ◽  
X Ray ◽  
Shot Classification ◽  
Object Proposals ◽  
The World

Screening baggage against potential threats has become one of the prime aviation security concerns all over the world, where manual detection of prohibited items is a time-consuming and hectic process. Many researchers have developed autonomous systems to recognize baggage threats using security X-ray scans. However, all of these frameworks are vulnerable against screening cluttered and concealed contraband items. Furthermore, to the best of our knowledge, no framework possesses the capacity to recognize baggage threats across multiple scanner specifications without an explicit retraining process. To overcome this, we present a novel meta-transfer learning-driven tensor-shot detector that decomposes the candidate scan into dual-energy tensors and employs a meta-one-shot classification backbone to recognize and localize the cluttered baggage threats. In addition, the proposed detection framework can be well-generalized to multiple scanner specifications due to its capacity to generate object proposals from the unified tensor maps rather than diversified raw scans. We have rigorously evaluated the proposed tensor-shot detector on the publicly available SIXray and GDXray datasets (containing a cumulative of 1,067,381 grayscale and colored baggage X-ray scans). On the SIXray dataset, the proposed framework achieved a mean average precision (mAP) of 0.6457, and on the GDXray dataset, it achieved the precision and F1 score of 0.9441 and 0.9598, respectively. Furthermore, it outperforms state-of-the-art frameworks by 8.03% in terms of mAP, 1.49% in terms of precision, and 0.573% in terms of F1 on the SIXray and GDXray dataset, respectively.

scholarly journals Translucent Answer Predictions in Multi-Hop Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7700-7707
Author(s):  
G P Shrivatsa Bhargav ◽  
Michael Glass ◽  
Dinesh Garg ◽  
Shirish Shevade ◽  
Saswati Dana ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Local Context ◽  
The Novel ◽  
Loose Coupling ◽  
Loosely Coupled ◽  
Neural Architecture ◽  
Coupled Networks ◽  
Novel Design

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

scholarly journals Finding the Perfect Match: Different Heavy-Duty Mobile Applications Call for Different Actuators

Proceedings ◽  
2020 ◽  
Vol 64 (1) ◽  
pp. 22
Author(s):  
David Fassbender ◽  
Tatina Minav
Keyword(s):  
Mobile Applications ◽  
State Of The Art ◽  
Perfect Match ◽  
The Novel ◽  
Hydraulic Systems ◽  
Heavy Duty ◽  
Different Types ◽  
Evaluation Algorithm ◽  
Novel Concept ◽  
Valve Control

For the longest time, valve-controlled, centralized hydraulic systems have been the state-of-the-art technology to actuate heavy-duty mobile machine (HDMM) implements. Due to the typically low energy efficiency of those systems, a high number of promising, more-efficient actuator concepts has been proposed by academia as well as industry over the last decades as potential replacements for valve control—e.g., independent metering, displacement control, different types of electro-hydraulic actuators (EHAs), electro-mechanic actuators, or hydraulic transformers. This paper takes a closer look on specific HDMM applications for these actuator concepts to figure out where which novel concept can be a better alternative to conventional actuator concepts, and where novel concepts might fail to improve. For this purpose, a novel evaluation algorithm for actuator–HDMM matches is developed based on problem aspects that can indicate an unsuitable actuator–HDMM match. To demonstrate the functionality of the match evaluation algorithm, four actuator concepts and four HDMM types are analyzed and rated in order to form 16 potential actuator–HDMM matches that can be evaluated by the novel algorithm. The four actuator concepts comprise a conventional valve-controlled concept and three different types of EHAs. The HDMM types are excavator, wheel loader, backhoe, and telehandler. Finally, the evaluation of the 16 matches results in 16 mismatch values, of which the lowest indicates the “perfect match”. Low mismatch values could be found in general for EHAs in combination with most HDMMs but also for a valve-controlled actuator concept in combination with a backhoe. Furthermore, an analysis of the concept limitations with suggestions for improvement is included.

scholarly journals Protein structure and sequence re-analysis of 2019-nCoV genome does not indicate snakes as its intermediate host or the unique similarity between its spike protein insertions and HIV-1

2020 ◽  
Author(s):  
Chengxin Zhang ◽  
Wei Zheng ◽  
Xiaoqiang Huang ◽  
Eric W. Bell ◽  
Xiaogen Zhou ◽  
...  
Keyword(s):  
State Of The Art ◽  
Careful Analysis ◽  
Spike Protein ◽  
The Novel ◽  
Intermediate Hosts ◽  
Cellular Mechanisms ◽  
Computational Approaches ◽  
Link Type ◽  
Hiv 1 ◽  
Existing Data

AbstractAs the infection of 2019-nCoV coronavirus is quickly developing into a global pneumonia epidemic, careful analysis of its transmission and cellular mechanisms is sorely needed. In this report, we re-analyzed the computational approaches and findings presented in two recent manuscripts by Ji et al. (https://doi.org/10.1002/jmv.25682) and by Pradhan et al. (https://doi.org/10.1101/2020.01.30.927871), which concluded that snakes are the intermediate hosts of 2019-nCoV and that the 2019-nCoV spike protein insertions shared a unique similarity to HIV-1. Results from our re-implementation of the analyses, built on larger-scale datasets using state-of-the-art bioinformatics methods and databases, do not support the conclusions proposed by these manuscripts. Based on our analyses and existing data of coronaviruses, we concluded that the intermediate hosts of 2019-nCoV are more likely to be mammals and birds than snakes, and that the “novel insertions” observed in the spike protein are naturally evolved from bat coronaviruses.

scholarly journals A dynamical systems view of network centrality

2014 ◽  
Vol 470 (2165) ◽  
pp. 20130835 ◽  
Author(s):  
Peter Grindrod ◽  
Desmond J. Higham
Keyword(s):  
Dynamical Systems ◽  
Large Scale ◽  
Dynamic Networks ◽  
Network Evolution ◽  
Mathematical Framework ◽  
The Novel ◽  
Matrix Logarithm ◽  
The Matrix ◽  
Systems View ◽  
Logarithm Function

To gain insights about dynamic networks, the dominant paradigm is to study discrete snapshots , or timeslices , as the interactions evolve. Here, we develop and test a new mathematical framework where network evolution is handled over continuous time, giving an elegant dynamical systems representation for the important concept of node centrality. The resulting system allows us to track the relative influence of each individual. This new setting is natural in many digital applications, offering both conceptual and computational advantages. The novel differential equations approach is convenient for modelling and analysis of network evolution and gives rise to an interesting application of the matrix logarithm function. From a computational perspective, it avoids the awkward up-front compromises between accuracy, efficiency and redundancy required in the prevalent discrete-time setting. Instead, we can rely on state-of-the-art ODE software, where discretization takes place adaptively in response to the prevailing system dynamics. The new centrality system generalizes the widely used Katz measure, and allows us to identify and track, at any resolution, the most influential nodes in terms of broadcasting and receiving information through time-dependent links. In addition to the classical static network notion of attenuation across edges, the new ODE also allows for attenuation over time, as information becomes stale. This allows ‘running measures’ to be computed, so that networks can be monitored in real time over arbitrarily long intervals. With regard to computational efficiency, we explain why it is cheaper to track good receivers of information than good broadcasters. An important consequence is that the overall broadcast activity in the network can also be monitored efficiently. We use two synthetic examples to validate the relevance of the new measures. We then illustrate the ideas on a large-scale voice call network, where key features are discovered that are not evident from snapshots or aggregates.

Efficiency Optimized Pneumatic Pressure Booster

2019 ◽  
Author(s):  
Olivier Reinertz ◽  
Katharina Schmitz
Keyword(s):  
Load Distribution ◽  
State Of The Art ◽  
Analytical Description ◽  
The Novel ◽  
One Dimensional ◽  
Pneumatic Pressure ◽  
Novel Device ◽  
Working Cycle ◽  
Promising Solution ◽  
Dimensional Simulation

Abstract In the scope of this paper, a novel efficiency optimized supply pressure adaptive concept of pneumatic pressure boosters is presented. It is deduced from a profound analysis of state of the art components. The working cycle of the pump chambers can be divided into a filling, compression, pumping and decompression phase. A promising solution for efficiency improvements, which is further analyzed in the scope of this paper, is to adapt the required force of the compression chambers by nonlinear mechanics. Thus, a smaller force at the end of the stroke is required and a reduced air consumption of the driving chamber occurs. As the force demand of the compression chamber and therewith the load distribution over the stroke changes with the operational pressures, an adaptive concept needs to be implemented. The novel device and its parameterization are deduced by means of an analytical description of state of the art pressure boosters. Subsequently, it is investigated by one-dimensional simulation in DSHplus. The results show broad applicability of the method in relevant applications and huge energy saving potentials compared to state of the art products.

scholarly journals A Hybrid Network for Large-Scale Action Recognition from RGB and Depth Modalities

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3305 ◽  
Author(s):  
Huogen Wang ◽  
Zhanjie Song ◽  
Wanqing Li ◽  
Pichao Wang
Keyword(s):  
Neural Network ◽  
Action Recognition ◽  
Canonical Correlation ◽  
Large Scale ◽  
State Of The Art ◽  
Hybrid Network ◽  
Support Vector ◽  
Multiple Modalities ◽  
Large Margin ◽  
Percentage Points

The paper presents a novel hybrid network for large-scale action recognition from multiple modalities. The network is built upon the proposed weighted dynamic images. It effectively leverages the strengths of the emerging Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) based approaches to specifically address the challenges that occur in large-scale action recognition and are not fully dealt with by the state-of-the-art methods. Specifically, the proposed hybrid network consists of a CNN based component and an RNN based component. Features extracted by the two components are fused through canonical correlation analysis and then fed to a linear Support Vector Machine (SVM) for classification. The proposed network achieved state-of-the-art results on the ChaLearn LAP IsoGD, NTU RGB+D and Multi-modal & Multi-view & Interactive ( M 2 I ) datasets and outperformed existing methods by a large margin (over 10 percentage points in some cases).

Sign in / Sign up

Export Citation Format

Share Document