scholarly journals AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches

2019 ◽  
Vol 33 ◽  
pp. 2564-2571 ◽  
Author(s):  
Nan Cao ◽  
Xin Yan ◽  
Yang Shi ◽  
Chaoran Chen
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
State Of The Art ◽  
Positional Information ◽  
Generative Model ◽  
Training Data ◽  
Creative Design ◽  
High Quality ◽  
User Input ◽  
Variational Autoencoder

Sketch drawings play an important role in assisting humans in communication and creative design since ancient period. This situation has motivated the development of artificial intelligence (AI) techniques for automatically generating sketches based on user input. Sketch-RNN, a sequence-to-sequence variational autoencoder (VAE) model, was developed for this purpose and known as a state-of-the-art technique. However, it suffers from limitations, including the generation of lowquality results and its incapability to support multi-class generations. To address these issues, we introduced AI-Sketcher, a deep generative model for generating high-quality multiclass sketches. Our model improves drawing quality by employing a CNN-based autoencoder to capture the positional information of each stroke at the pixel level. It also introduces an influence layer to more precisely guide the generation of each stroke by directly referring to the training data. To support multi-class sketch generation, we provided a conditional vector that can help differentiate sketches under various classes. The proposed technique was evaluated based on two large-scale sketch datasets, and results demonstrated its power in generating high-quality sketches.

57 Precision neoantigen discovery using novel algorithms and expanded HLA-ligandome datasets

2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A62-A62
Author(s):  
Dattatreya Mellacheruvu ◽  
Rachel Pyke ◽  
Charles Abbott ◽  
Nick Phillips ◽  
Sejal Desai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cell Lines ◽  
Antigen Processing ◽  
Large Scale ◽  
Prediction Models ◽  
K562 Cells ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
High Quality ◽  
Tissue Samples

BackgroundAccurately identified neoantigens can be effective therapeutic agents in both adjuvant and neoadjuvant settings. A key challenge for neoantigen discovery has been the availability of accurate prediction models for MHC peptide presentation. We have shown previously that our proprietary model based on (i) large-scale, in-house mono-allelic data, (ii) custom features that model antigen processing, and (iii) advanced machine learning algorithms has strong performance. We have extended upon our work by systematically integrating large quantities of high-quality, publicly available data, implementing new modelling algorithms, and rigorously testing our models. These extensions lead to substantial improvements in performance and generalizability. Our algorithm, named Systematic HLA Epitope Ranking Pan Algorithm (SHERPA™), is integrated into the ImmunoID NeXT Platform®, our immuno-genomics and transcriptomics platform specifically designed to enable the development of immunotherapies.MethodsIn-house immunopeptidomic data was generated using stably transfected HLA-null K562 cells lines that express a single HLA allele of interest, followed by immunoprecipitation using W6/32 antibody and LC-MS/MS. Public immunopeptidomics data was downloaded from repositories such as MassIVE and processed uniformly using in-house pipelines to generate peptide lists filtered at 1% false discovery rate. Other metrics (features) were either extracted from source data or generated internally by re-processing samples utilizing the ImmunoID NeXT Platform.ResultsWe have generated large-scale and high-quality immunopeptidomics data by using approximately 60 mono-allelic cell lines that unambiguously assign peptides to their presenting alleles to create our primary models. Briefly, our primary ‘binding’ algorithm models MHC-peptide binding using peptide and binding pockets while our primary ‘presentation’ model uses additional features to model antigen processing and presentation. Both primary models have significantly higher precision across all recall values in multiple test data sets, including mono-allelic cell lines and multi-allelic tissue samples. To further improve the performance of our model, we expanded the diversity of our training set using high-quality, publicly available mono-allelic immunopeptidomics data. Furthermore, multi-allelic data was integrated by resolving peptide-to-allele mappings using our primary models. We then trained a new model using the expanded training data and a new composite machine learning architecture. The resulting secondary model further improves performance and generalizability across several tissue samples.ConclusionsImproving technologies for neoantigen discovery is critical for many therapeutic applications, including personalized neoantigen vaccines, and neoantigen-based biomarkers for immunotherapies. Our new and improved algorithm (SHERPA) has significantly higher performance compared to a state-of-the-art public algorithm and furthers this objective.

Thermal Laser Separation – A Novel Dicing Technology Fulfilling the Demands of Volume Manufacturing of 4H-SiC Devices

2015 ◽  
Vol 821-823 ◽  
pp. 528-532 ◽  
Author(s):  
Dirk Lewke ◽  
Karl Otto Dohnke ◽  
Hans Ulrich Zühlke ◽  
Mercedes Cerezuela Barret ◽  
Martin Schellenberger ◽  
...  
Keyword(s):  
Experimental Data ◽  
Process Control ◽  
Tool Wear ◽  
Large Scale ◽  
State Of The Art ◽  
Scale Production ◽  
High Quality ◽  
Large Scale Production ◽  
Laser Separation

One challenge for volume manufacturing of 4H-SiC devices is the state-of-the-art wafer dicing technology – the mechanical blade dicing which suffers from high tool wear and low feed rates. In this paper we discuss Thermal Laser Separation (TLS) as a novel dicing technology for large scale production of SiC devices. We compare the latest TLS experimental data resulting from fully processed 4H-SiC wafers with results obtained by mechanical dicing technology. Especially typical product relevant features like process control monitoring (PCM) structures and backside metallization, quality of diced SiC-devices as well as productivity are considered. It could be shown that with feed rates up to two orders of magnitude higher than state-of-the-art, no tool wear and high quality of diced chips, TLS has a very promising potential to fulfill the demands of volume manufacturing of 4H-SiC devices.

scholarly journals Attending to Entities for Better Text Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 7554-7561
Author(s):  
Pengxiang Cheng ◽  
Katrin Erk
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
State Of The Art ◽  
Syntactic Structure ◽  
Semantic Knowledge ◽  
Training Data ◽  
Language Models ◽  
Long Distance ◽  
Future Directions ◽  
Text Understanding

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art results, approaching human performance. This clearly demonstrates the power of the stacked self-attention architecture when paired with a sufficient number of layers and a large amount of pre-training data. However, on tasks that require complex and long-distance reasoning where surface-level cues are not enough, there is still a large gap between the pre-trained models and human performance. Strubell et al. (2018) recently showed that it is possible to inject knowledge of syntactic structure into a model through supervised self-attention. We conjecture that a similar injection of semantic knowledge, in particular, coreference information, into an existing model would improve performance on such complex problems. On the LAMBADA (Paperno et al. 2016) task, we show that a model trained from scratch with coreference as auxiliary supervision for self-attention outperforms the largest GPT-2 model, setting the new state-of-the-art, while only containing a tiny fraction of parameters compared to GPT-2. We also conduct a thorough analysis of different variants of model architectures and supervision configurations, suggesting future directions on applying similar techniques to other problems.

scholarly journals Exemplar Guided Neural Dialogue Generation

2020 ◽  
Author(s):  
Hengyi Cai ◽  
Hongshen Chen ◽  
Yonghao Song ◽  
Xiaofang Zhao ◽  
Dawei Yin
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Small Subset ◽  
Generation Model ◽  
Retrieval Model ◽  
Training Set ◽  
Dialogue Model ◽  
Quantitative Metrics ◽  
The Given

Humans benefit from previous experiences when taking actions. Similarly, related examples from the training data also provide exemplary information for neural dialogue models when responding to a given input message. However, effectively fusing such exemplary information into dialogue generation is non-trivial: useful exemplars are required to be not only literally-similar, but also topic-related with the given context. Noisy exemplars impair the neural dialogue models understanding the conversation topics and even corrupt the response generation. To address the issues, we propose an exemplar guided neural dialogue generation model where exemplar responses are retrieved in terms of both the text similarity and the topic proximity through a two-stage exemplar retrieval model. In the first stage, a small subset of conversations is retrieved from a training set given a dialogue context. These candidate exemplars are then finely ranked regarding the topical proximity to choose the best-matched exemplar response. To further induce the neural dialogue generation model consulting the exemplar response and the conversation topics more faithfully, we introduce a multi-source sampling mechanism to provide the dialogue model with both local exemplary semantics and global topical guidance during decoding. Empirical evaluations on a large-scale conversation dataset show that the proposed approach significantly outperforms the state-of-the-art in terms of both the quantitative metrics and human evaluations.

scholarly journals CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Aboubakar Nasser Samatin Njikam ◽  
Huan Zhao
Keyword(s):  
Text Classification ◽  
Building Block ◽  
Large Scale ◽  
State Of The Art ◽  
Building Blocks ◽  
Training Data ◽  
Superior Performance ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

scholarly journals Facing small and biased data dilemma in drug discovery with federated learning

2020 ◽  
Author(s):  
Zhaoping Xiong ◽  
Ziqiang Cheng ◽  
Chi Xu ◽  
Xinyuan Lin ◽  
Xiaohong Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Drug Discovery ◽  
Aqueous Solubility ◽  
Training Data ◽  
Small Data ◽  
Sensitive Information ◽  
Distributed Data ◽  
High Quality ◽  
Different Sources ◽  
Striking Contrast

AbstractArtificial intelligence (AI) models usually require large amounts of high-quality training data, which is in striking contrast to the situation of small and biased data faced by current drug discovery pipelines. The concept of federated learning has been proposed to utilize distributed data from different sources without leaking sensitive information of these data. This emerging decentralized machine learning paradigm is expected to dramatically improve the success of AI-powered drug discovery. We here simulate the federated learning process with 7 aqueous solubility datasets from different sources, among which there are overlapping molecules with high or low biases in the recorded values. Beyond the benefit of gaining more data, we also demonstrate federated training has a regularization effect making it superior than centralized training on the pooled datasets with high biases. Further, two more cases are studied to test the usability of federated learning in drug discovery. Our work demonstrates the application of federated learning in predicting drug related properties, but also highlights its promising role in addressing the small data and biased data dilemma in drug discovery.

scholarly journals Periodismo de alta tecnología: signo de los tiempos digitales del tercer milenio

2021 ◽  
Author(s):  
Xosé López-García ◽  
Ángel Vizoso
Keyword(s):  
Artificial Intelligence ◽  
State Of The Art ◽  
High Technology ◽  
The State ◽  
Current Phase ◽  
Quality Information ◽  
High Quality ◽  
Daily Routines ◽  
High Quality Information ◽  
The Media

High technology is driving most of the innovation and debates in journalism today. Artificial intelligence and journalism are walking hand in hand in the current phase, defined by processes of digitization. Studies on the state of the art of such technology in the media reveal a clear tendency towards the use of more sophisticated tools. Furthermore, this research highlights how journalists are increasingly using such approaches in challenging situations. This shift has thus led to more debate on the threats and opportunities of the introduction of such technologies into a communication ecosystem that is already in need of models that can produce high-quality information. This study thus describes the state of the art on the integration of high technology into daily routines in the media. Resumen La denominada “alta tecnología” marca buena parte de la innovación y de los debates del periodismo actual. Inteligencia artificial y periodismo caminan de la mano en la fase actual de la digitalización de los procesos. Los estudios sobre el estado de las tecnologías en las redacciones de los medios muestran una clara tendencia de los periodistas a trabajar con herramientas más sofisticadas y a emplearlas en los desafíos que tienen a la hora de realizar su cometido profesional. La tendencia, que no parece tener marcha atrás, introduce renovados debates sobre las amenazas y oportunidades en un ecosistema comunicativo cada vez más complejo y más necesitado de respuestas para establecer modelos sostenibles que aseguren la existencia de información periodística de calidad. En este texto se realiza una aproximación al estado de la cuestión, se analizan experiencias y se sitúan algunos de los retos.

scholarly journals Learn to Train: Improving Training Data for a Neural Network to Detect Pecking Injuries in Turkeys

Animals ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 2655
Author(s):  
Nina Volkmann ◽  
Johannes Brünger ◽  
Jenny Stracke ◽  
Claudius Zelenka ◽  
Reinhard Koch ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Automated Detection ◽  
Training Data ◽  
High Quality

This study aimed to develop a camera-based system using artificial intelligence for automated detection of pecking injuries in turkeys. Videos were recorded and split into individual images for further processing. Using specifically developed software, the injuries visible on these images were marked by humans, and a neural network was trained with these annotations. Due to unacceptable agreement between the annotations of humans and the network, several work steps were initiated to improve the training data. First, a costly work step was used to create high-quality annotations (HQA) for which multiple observers evaluated already annotated injuries. Therefore, each labeled detection had to be validated by three observers before it was saved as “finished”, and for each image, all detections had to be verified three times. Then, a network was trained with these HQA to assist observers in annotating more data. Finally, the benefit of the work step generating HQA was tested, and it was shown that the value of the agreement between the annotations of humans and the network could be doubled. Although the system is not yet capable of ensuring adequate detection of pecking injuries, the study demonstrated the importance of such validation steps in order to obtain good training data.

scholarly journals Proactive Construction of an Annotated Imaging Database for Artificial Intelligence Training

2020 ◽  
Author(s):  
Caroline Bivik Stadler ◽  
Martin Lindvall ◽  
Claes Lundström ◽  
Anna Bodén ◽  
Karin Lindman ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Image Data ◽  
Ground Truth ◽  
Lessons Learned ◽  
Training Data ◽  
Imaging Data ◽  
High Quality ◽  
High Quality Image ◽  
Specific Objective ◽  
Wide Range

Abstract Artificial intelligence (AI) holds much promise for enabling highly desired imaging diagnostics improvements. One of the most limiting bottlenecks for the development of useful clinical-grade AI models is the lack of training data. One aspect is the large amount of cases needed and another is the necessity of high-quality ground truth annotation. The aim of the project was to establish and describe the construction of a database with substantial amounts of detail-annotated oncology imaging data from pathology and radiology. A specific objective was to be proactive, that is, to support undefined subsequent AI training across a wide range of tasks, such as detection, quantification, segmentation, and classification, which puts particular focus on the quality and generality of the annotations. The main outcome of this project was the database as such, with a collection of labeled image data from breast, ovary, skin, colon, skeleton, and liver. In addition, this effort also served as an exploration of best practices for further scalability of high-quality image collections, and a main contribution of the study was generic lessons learned regarding how to successfully organize efforts to construct medical imaging databases for AI training, summarized as eight guiding principles covering team, process, and execution aspects.

scholarly journals Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

2019 ◽  
Vol 33 ◽  
pp. 273-280 ◽  
Author(s):  
Xiaoxiao Sun ◽  
Liyi Chen ◽  
Jufeng Yang
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Web Data ◽  
Fine Grained ◽  
Learning Framework ◽  
Attractive Option ◽  
Public Datasets ◽  
Noisy Labels

Fine-grained classification is absorbed in recognizing the subordinate categories of one field, which need a large number of labeled images, while it is expensive to label these images. Utilizing web data has been an attractive option to meet the demands of training data for convolutional neural networks (CNNs), especially when the well-labeled data is not enough. However, directly training on such easily obtained images often leads to unsatisfactory performance due to factors such as noisy labels. This has been conventionally addressed by reducing the noise level of web data. In this paper, we take a fundamentally different view and propose an adversarial discriminative loss to advocate representation coherence between standard and web data. This is further encapsulated in a simple, scalable and end-to-end trainable multi-task learning framework. We experiment on three public datasets using large-scale web data to evaluate the effectiveness and generalizability of the proposed approach. Extensive experiments demonstrate that our approach performs favorably against the state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document