Search
Now showing items 1-20 of 28
DeepSampling: Image Sampling Technique for Cost-Effective Deep Learning
(2020)
, and Stanford dog. The results confirm that the accuracies obtained by DeepSampling are improved by approximately 2-3% for image classification, compared to traditional evaluation techniques on the same dataset....
SigsSpace-Text: Parallel and Distributed Signature Learning in Text Analytics
(University of Missouri--Kansas City, 2016)
is identified for a given category using state-of-the-art clustering algorithms, i.e., K-Means, Self-Organizing Maps (SOM), and Gaussian Mixture Models (GMM). These signatures are used (instead of raw data) as a feature set to the classification. Through...
Dynamic Activity Predictions using Graph-based Neural Networks for Time Series Forecasting
(2023)
Time series forecasting is a vital task in numerous fields, and traditional methods,
machine learning models, and neural graph networks have been employed to improve
prediction accuracy. However, these techniques need ...
Shared Context through Multi-Level Attention Transformers for Text Classification
(2021)
Natural language processing (NLP) has seen recent explosive growth by creating artificial intelligence with human-level intelligence. Understanding the context using an attention mechanism could be further improved by ...
AudioCNN: Audio Event Classification With Deep Learning Based Multi-Channel Fusion Networks
(2020)
techniques. We have conducted our extensive experiments with benchmark datasets, including Urbansound8k, ESC-50, and ESC-10, emotion datasets. We have obtained state-of-the-art results by outperforming the previous solutions. The experiment results show...
MDRED: Multi-Modal Multi-Task Distributed Recognition for Event Detection
(University of Missouri -- Kansas City, 2018)
Understanding users’ context is essential in emerging mobile sensing applications, such
as Metal Detector, Glint Finder, Facefirst. Over the last decade, Machine Learning (ML)
techniques have evolved dramatically for ...
Distributed Collaborative Framework for Deep Learning in Object Detection
(2020)
Object detection has gained much attention in recent years because of its ability to localize and classify the objects in videos and images that can be incorporated into many applications. Traditional object detection algorithms need substantial...
Class Representative Projection for Text-based Zero-Shot Learning
(2020)
) sentence-based embeddings, (2) deep neural networks, and (3) class-based representative classifiers. Experimental results show that the proposed projection framework achieves the best classification results in text-based ZSL/G-ZSL compared with the state-of-the-art...
Multi-Modal Topic Sentiment Analytics for Twitter
(University of Missouri -- Kansas City, 2018)
Sentiment analysis has proven to be very successful in text applications. Social media
is also considered a quite rich source to get data regarding user’s behaviors and
preference. Identifying social context would make ...
Context Based Multi-Image Visual Question Answering (VQA) in Deep Learning
(University of Missouri--Kansas City, 2017)
Image question answering has gained huge popularity in recent years due to
advancements in Deep Learning technologies and computer processing hardware which are
able to achieve higher accuracies with faster processing ...
KB4DL: Building a Knowledge Base for Deep Learning
(University of Missouri -- Kansas City, 2019)
Deep Learning (DL) has received considerable attention from the AI community. However, we
suffer from the lack of ability in interpretation and annotation of the outcomes from
extensive and exhausting learning efforts. ...
SigSpace – Class-Based Feature Representation for Scalable and Distributed Machine Learning
(University of Missouri–Kansas City, 2016)
In the era of big data, it is essential to explore the opportunities in discovering knowledge
from big data. However, traditional machine learning approaches are not well fit
to analyze the full value of big data. ...
Domain Playground: Extending Deep Learning Models to Open Domain Boundaries
(2021)
Deep learning models have demonstrated monumental performance in classification tasks but require extensive data and training procedures to converge. Additionally, the performance is only guaranteed when there is no domain ...
DL-DI: A Deep Learning Framework for Distributed, Incremental Image Classification
(University of Missouri--Kansas City, 2017)
Deep Learning technologies show promise for dramatic advances in fields such as image
classification and speech recognition. Deep Learning (DL) is a class of Machine Learning algorithms
that involves learning of multiple ...
Social Bridge: searching beyond Friend of a Friend networks
(University of Missouri--Kansas City, 2012-06-11)
Social networking has turned into an integral constituent in our lives. There appears
to be an imperative demand for finding and linking with others to share one's day-to-day
activities. However, currently available ...
Multiple-valued logic: technology and circuit implementation
(2021)
Transistor (CNTFET). A comparative analysis of the proposed designs and several state-of-the-art designs are also given in all the cases in terms of delay, total power, and power-delay-product (PDP). The simulation and analysis are performed using the H...
Automated End-to-End Management of the Deep Learning Lifecycle
(2020)
Deep learning has improved the state-of-the-art results in an ever-growing number of domains. This success heavily relies on the development of deep learning models--an experimental, iterative process that produces tens to hundreds of models before...
StoryNet: A 5W1H-based knowledge graph to connect stories
(2021)
Stories are a powerful medium through which the human community has exchanged information since the dawn of the information age. They have taken multiple forms like articles, movies, books, plays, short films, magazines, ...
On-chip Voltage Regulator– Circuit Design and Automation
(2021)
With the increase of density and complexity of high-performance integrated circuits and systems, including many-core chips and system-on-chip (SoC), it is becoming difficult to meet the power delivery and regulation ...
Explainable AI framework through Multi-Context Multi-Dimensional Graph Neural Network
(2023)
sentiment analysis and topic modeling, were employed to interpret this vast data ocean. However, traditional algorithms struggled to encapsulate the intricate interconnections in social media ecosystems, focus group interactions, and classic literature...