scholarly journals Coarse-grained spectral projection: A deep learning assisted approach to quantum unitary dynamics

2021 ◽  
Vol 103 (2) ◽  
Author(s):  
Pinchen Xie ◽  
Weinan E
Keyword(s):  
Deep Learning ◽  
Spectral Projection ◽  
Coarse Grained

scholarly journals Simba

2021 ◽  
Vol 64 (6) ◽  
pp. 107-116
Author(s):  
Yakun Sophia Shao ◽  
Jason Cemons ◽  
Rangharajan Venkatesan ◽  
Brian Zimmer ◽  
Matthew Fojtik ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Data Locality ◽  
Coarse Grained ◽  
Batch Size ◽  
Peak Performance ◽  
Large Scale Systems ◽  
High Area ◽  
On Chip ◽  
And Storage

Package-level integration using multi-chip-modules (MCMs) is a promising approach for building large-scale systems. Compared to a large monolithic die, an MCM combines many smaller chiplets into a larger system, substantially reducing fabrication and design costs. Current MCMs typically only contain a handful of coarse-grained large chiplets due to the high area, performance, and energy overheads associated with inter-chiplet communication. This work investigates and quantifies the costs and benefits of using MCMs with finegrained chiplets for deep learning inference, an application domain with large compute and on-chip storage requirements. To evaluate the approach, we architected, implemented, fabricated, and tested Simba, a 36-chiplet prototype MCM system for deep-learning inference. Each chiplet achieves 4 TOPS peak performance, and the 36-chiplet MCM package achieves up to 128 TOPS and up to 6.1 TOPS/W. The MCM is configurable to support a flexible mapping of DNN layers to the distributed compute and storage units. To mitigate inter-chiplet communication overheads, we introduce three tiling optimizations that improve data locality. These optimizations achieve up to 16% speedup compared to the baseline layer mapping. Our evaluation shows that Simba can process 1988 images/s running ResNet-50 with a batch size of one, delivering an inference latency of 0.50 ms.

scholarly journals Classification & Detection of Vehicles using Deep Learning

2020 ◽  
Vol 9 (7) ◽  
pp. 181-189
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Transportation Systems ◽  
Coarse Grained ◽  
Vehicle Classification ◽  
Training Dataset ◽  
License Plate ◽  
Original Dataset ◽  
Detection Of Objects

The vehicle classification and detecting its license plate are important tasks in intelligent security and transportation systems. However, theexisting methods of vehicle classification and detection are highly complex which provides coarse-grained outcomesbecause of underfitting or overfitting of the model. Due toadvanced accomplishmentsof the Deep Learning, it was efficiently implemented to image classification and detection of objects. This proposed paper come up with a new approach which makes use of convolutional neural networks concept in Deep Learning.It consists of two steps: i) vehicle classification ii) vehicle license plate recognition. Numerous classicmodules of neural networks hadbeen implemented in training and testing the vehicle classification and detection of license plate model, such as CNN (convolutional neural networks), TensorFlow, and Tesseract-OCR. The suggestedtechnique candetermine the vehicle type, number plate and other alternative dataeffectively. This model provides security and log details regarding vehicles by using AI Surveillance. It guides the surveillance operators and assists human resources. With the help of the original dataset (training) and enriched dataset (testing), this customized model(algorithm) can achieve best outcomewith a standard accuracy of around 97.32% inclassification and detection of vehicles. By enlarging the quantity of the training dataset, the loss function and mislearning rate declines progressively. Therefore, this proposedmodelwhich uses DeepLearning hadbetterperformance and flexibility. When compared to outstandingtechniques in the strategicImage datasets, this deep learning modelscan gethigher competitor outcomes. Eventually, the proposed system suggests modern methods for advancementof the customized model and forecasts the progressivegrowth of deep learningperformance in the explorationof artificial intelligence (AI) &machine learning (ML) techniques.

scholarly journals High-throughput prediction of stress–strain curves of thermoplastic elastomer model block copolymers by combining hierarchical simulation and deep learning

MRS Advances ◽  
2021 ◽  
Author(s):  
Takeshi Aoyagi
Keyword(s):  
Deep Learning ◽  
High Throughput ◽  
High Throughput Screening ◽  
Thermoplastic Elastomer ◽  
Thermoplastic Elastomers ◽  
Coarse Grained ◽  
Stress Strain ◽  
Self Consistent Field ◽  
Self Consistent Field Theory ◽  
Dynamics Simulations

Abstract We achieved high-throughput prediction of the stress–strain (S–S) curves of thermoplastic elastomers by combining hierarchical simulation and deep learning. ABA triblock copolymer with a phase-separated structure was used as a thermoplastic elastomer model. The S–S curves of the ABA triblock copolymers were calculated from the hierarchical simulation of self-consistent field theory calculations and coarse-grained molecular dynamics simulations. Because such hierarchical simulations require considerable computational resources, we applied a deep learning technique to accelerate the prediction. Sets of phase-separated structures and the S–S curves obtained from the hierarchical simulation were used to train a 3D convolutional neural network. Using the trained network, we confirmed that the predicted S–S curves of the untrained structures accurately reproduced the simulation results. These results will enable us to design novel polymers and phase-separated structures with desired S–S curves by high-throughput screening of a wide variety of structures. Graphic abstract

scholarly journals A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Qinghe Zheng ◽  
Mingqiang Yang ◽  
Xinyu Tian ◽  
Nan Jiang ◽  
Deqiang Wang
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Network Architecture ◽  
Data Augmentation ◽  
Coarse Grained ◽  
Natural Image ◽  
Deep Convolutional Neural Networks ◽  
Specific Domain ◽  
Training Costs ◽  
Model Training

Nowadays, deep learning has achieved remarkable results in many computer vision related tasks, among which the support of big data is essential. In this paper, we propose a full stage data augmentation framework to improve the accuracy of deep convolutional neural networks, which can also play the role of implicit model ensemble without introducing additional model training costs. Simultaneous data augmentation during training and testing stages can ensure network optimization and enhance its generalization ability. Augmentation in two stages needs to be consistent to ensure the accurate transfer of specific domain information. Furthermore, this framework is universal for any network architecture and data augmentation strategy and therefore can be applied to a variety of deep learning based tasks. Finally, experimental results about image classification on the coarse-grained dataset CIFAR-10 (93.41%) and fine-grained dataset CIFAR-100 (70.22%) demonstrate the effectiveness of the framework by comparing with state-of-the-art results.

scholarly journals Technical Domain Classification of Bangla Text using BERT

2021 ◽  
Author(s):  
Koyel Ghosh ◽  
Apurbalal Senapati
Keyword(s):  
Deep Learning ◽  
Computer Science ◽  
Communication Technology ◽  
Text Classification ◽  
Language Model ◽  
Learning Model ◽  
Coarse Grained ◽  
Deep Learning Model

Coarse-grained tasks are primarily based on Text classification, one of the earliest problems in NLP, and these tasks are done on document and sentence levels. Here, our goal is to identify the technical domain of a given Bangla text. In Coarse-grained technical domain classification, such a piece of the Bangla text provides information about specific Coarse-grained technical domains like Biochemistry (bioche), Communication Technology (com-tech), Computer Science (cse), Management (mgmt), Physics (phy) Etc. This paper uses a recent deep learning model called the Bangla Bidirectional Encoder Representations Transformers (Bangla BERT) mechanism to identify the domain of a given text. Bangla BERT (Bangla-Bert-Base) is a pretrained language model of the Bangla language. Later, we discuss the Bangla BERT accuracy and compare it with other models that solve the same problem.

scholarly journals Deep learning enables the atomic structure determination of the Fanconi Anemia core complex from cryoEM

IUCrJ ◽  
2020 ◽  
Vol 7 (5) ◽  
pp. 881-892
Author(s):  
Daniel P. Farrell ◽  
Ivan Anishchenko ◽  
Shabih Shakeel ◽  
Anna Lauko ◽  
Lori A. Passmore ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fanconi Anemia ◽  
Structure Determination ◽  
Model Building ◽  
Protein Complexes ◽  
Structural Features ◽  
Coarse Grained ◽  
Core Complex ◽  
Distance Distributions

Cryo-electron microscopy of protein complexes often leads to moderate resolution maps (4–8 Å), with visible secondary-structure elements but poorly resolved loops, making model building challenging. In the absence of high-resolution structures of homologues, only coarse-grained structural features are typically inferred from these maps, and it is often impossible to assign specific regions of density to individual protein subunits. This paper describes a new method for overcoming these difficulties that integrates predicted residue distance distributions from a deep-learned convolutional neural network, computational protein folding using Rosetta, and automated EM-map-guided complex assembly. We apply this method to a 4.6 Å resolution cryoEM map of Fanconi Anemia core complex (FAcc), an E3 ubiquitin ligase required for DNA interstrand crosslink repair, which was previously challenging to interpret as it comprises 6557 residues, only 1897 of which are covered by homology models. In the published model built from this map, only 387 residues could be assigned to the specific subunits with confidence. By building and placing into density 42 deep-learning-guided models containing 4795 residues not included in the previously published structure, we are able to determine an almost-complete atomic model of FAcc, in which 5182 of the 6557 residues were placed. The resulting model is consistent with previously published biochemical data, and facilitates interpretation of disease-related mutational data. We anticipate that our approach will be broadly useful for cryoEM structure determination of large complexes containing many subunits for which there are no homologues of known structure.

scholarly journals A Deep Learning Based Printing Defect Classification Method with Imbalanced Samples

Symmetry ◽  
2019 ◽  
Vol 11 (12) ◽  
pp. 1440 ◽  
Author(s):  
Erhu Zhang ◽  
Bo Li ◽  
Peilin Li ◽  
Yajun Chen
Keyword(s):  
Deep Learning ◽  
Classification Method ◽  
Coarse Grained ◽  
Defect Classification ◽  
Accuracy Rate ◽  
Practical Applications ◽  
Fine Grained ◽  
Deep Model ◽  
Different Types ◽  
Classification Tasks

Deep learning has been successfully applied to classification tasks in many fields due to its good performance in learning discriminative features. However, the application of deep learning to printing defect classification is very rare, and there is almost no research on the classification method for printing defects with imbalanced samples. In this paper, we present a deep convolutional neural network model to extract deep features directly from printed image defects. Furthermore, considering the asymmetry in the number of different types of defect samples—that is, the number of different kinds of defect samples is unbalanced—seven types of over-sampling methods were investigated to determine the best method. To verify the practical applications of the proposed deep model and the effectiveness of the extracted features, a large dataset of printing detect samples was built. All samples were collected from practical printing products in the factory. The dataset includes a coarse-grained dataset with four types of printing samples and a fine-grained dataset with eleven types of printing samples. The experimental results show that the proposed deep model achieves a 96.86% classification accuracy rate on the coarse-grained dataset without adopting over-sampling, which is the highest accuracy compared to the well-known deep models based on transfer learning. Moreover, by adopting the proposed deep model combined with the SVM-SMOTE over-sampling method, the accuracy rate is improved by more than 20% in the fine-grained dataset compared to the method without over-sampling.

scholarly journals Deep learning enables the atomic structure determination of the Fanconi Anemia core complex from cryoEM

2020 ◽  
Author(s):  
Daniel P. Farrell ◽  
Ivan Anishchenko ◽  
Shabih Shakeel ◽  
Anna Lauko ◽  
Lori A. Passmore ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fanconi Anemia ◽  
Structure Determination ◽  
Model Building ◽  
Protein Complexes ◽  
Structural Features ◽  
Coarse Grained ◽  
Core Complex ◽  
Distance Distributions

AbstractCryo-electron microscopy of protein complexes often leads to moderate resolution maps (4-8 Å), with visible secondary structure elements but poorly resolved loops, making model-building challenging. In the absence of high-resolution structures of homologues, only coarse-grained structural features are typically inferred from these maps, and it is often impossible to assign specific regions of density to individual protein subunits. This paper describes a new method for overcoming these difficulties that integrates predicted residue distance distributions from a deep-learned convolutional neural network, computational protein folding using Rosetta, and automated EM-map-guided complex assembly. We apply this method to a 4.6 Å resolution cryoEM map of Fanconi Anemia core complex (FAcc), an E3 ubiquitin ligase required for DNA interstrand crosslink repair, which was previously challenging to interpret as it is comprised of 6557 residues, only 1897 of which are covered by homology models. In the published structure built from this map, only 387 residues could be assigned to specific subunits. By building and placing into density 42 deep-learning guided models containing 4795 residues not included in the previously published structure, we are able to determine an almost-complete atomic model of FAcc, in which 5182 of the 6557 residues were placed. The resulting model is consistent with previously published biochemical data, and facilitates interpretation of disease related mutational data. We anticipate that our approach will be broadly useful for cryoEM structure determination of large complexes containing many subunits for which there are no homologues of known structure.

scholarly journals A Deep Learning Account of How Language Affects Thought

2021 ◽  
Author(s):  
Xiaoliang Luo ◽  
Nicholas J. Sexton ◽  
Bradley C. Love
Keyword(s):  
Deep Learning ◽  
Language Learning ◽  
Coarse Grained ◽  
Semantic Representations ◽  
Visual Stream ◽  
Fine Grained ◽  
Linguistic Label ◽  
Underlying Theory ◽  
Ventral Visual Stream ◽  
Label Use

How can words shape meaning? Shared labels highlight commonalities between concepts whereas contrasting labels make differences apparent. To address such findings, we propose a deep learning account that spans perception to decision (i.e., labelling). The model takes photographs as input, transforms them to semantic representations through computations that parallel the ventral visual stream, and finally determines the appropriate linguistic label. The underlying theory is that minimising error on two prediction tasks (predicting the meaning and label of a stimulus) requires a compromise in the network's semantic representations. Thus, differences in label use, whether across languages or levels of expertise, manifest in differences in the semantic representations that support label discrimination. We confirm these predictions in simulations involving fine-grained and coarse-grained labels. We hope these and allied efforts which model perception, semantics, and labelling at scale will advance developmental and neurocomputational accounts of concept and language learning.

Sign in / Sign up

Export Citation Format

Share Document