Filters








838 Hits in 5.6 sec

Artificial Intelligence for Speech Recognition Based on Neural Networks

Takialddin Al Smadi, Huthaifa A. Al Issa, Esam Trad, Khalid A. Al Smadi
2015 Journal of Signal and Information Processing  
signals and neural networks of irregular users.  ...  Approach: Studying the possibility of designing a software system using one of the techniques of artificial intelligence applications neuron networks where this system is able to distinguish the sound  ...  The neural network has qualities that are inherent in the so-called artificial intelligence [11] . Conclusion Model of speech recognition was based on artificial neural networks.  ... 
doi:10.4236/jsip.2015.62006 fatcat:y5ieaszadnaxnnlkfzvzysk7ye

Asynchronous Mini-Batch Gradient Descent with Variance Reduction for Non-Convex Optimization

Zhouyuan Huo, Heng Huang
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We evaluate our methods by optimizing multi-layer neural networks on two real datasets (MNIST and CIFAR-10), and experimental results demonstrate our theoretical analysis.  ...  We provide the first theoretical analysis on the convergence rate of asynchronous mini-batch gradient descent with variance reduction (AsySVRG) for non-convex optimization.  ...  We train this neural network with softmax loss function, and 2 regularization with weight C = 10 −3 . We set mini-batch size |I t | = 10, and inner iteration length m = 1, 000.  ... 
doi:10.1609/aaai.v31i1.10940 fatcat:hfi4mka5gndehgfhicd2rsnyzy

A thousand brains: toward biologically constrained AI

Kjell Jørgen Hole, Subutai Ahmad
2021 SN Applied Sciences  
AbstractThis paper reviews the state of artificial intelligence (AI) and the quest to create general AI with human-like cognitive capabilities.  ...  Finally, the article concludes that AI researchers and neuroscientists should work together on specified topics to achieve biologically constrained AI with human-like capabilities.  ...  It is a family of statistical techniques for classifying patterns using artificial neural networks with many layers.  ... 
doi:10.1007/s42452-021-04715-0 fatcat:3zmlzxcvvbf7tbpnjkuqz5okx4

Keeping a Distance-Education Course Current Through eLearning and Contextual Assessment

Adrian A. Hopgood, Anthony J. Hirst
2007 IEEE Transactions on Education  
The assessment strategy aims to maintain currency by introducing the latest contexts in which artificial intelligence is used.  ...  The Open University course T396: Artificial Intelligence for Technology makes use of electronic delivery and a carefully designed assessment strategy to address the challenge of keeping the course up-to-date  ...  Block 1 covers knowledge-based systems, fuzzy logic and intelligent agents, while Block 2 covers computational intelligence techniques, including genetic algorithms and neural networks.  ... 
doi:10.1109/te.2006.888905 fatcat:ogt3w2vtjjftrltvdroh6uds6y

New directions for medical artificial intelligence

V.K. Sondak, N.E. Sondak
1990 Computers and Mathematics with Applications  
ARTIFICIAL INTELLIGENCE IN MEDICINE  ...  Al~tract--The past decade has seen significant advances in medical artificial intelligence (MAI), but its role in medicine and medical education remains fimited.  ...  machines that emulate neural networks, and new chips that simulate artificial neural systems.  ... 
doi:10.1016/0898-1221(90)90336-i fatcat:22pzuhyzrvgdzjhtyrpm77aupq

March 2021: Top Read Articles in Soft Computing

IJSC
2021 Zenodo  
[3] "Artificial Neural Networks" ocw.mit.edu [4] Dr. U. C. Sahoo Dr. U. C.  ...  Her areas of interests include Soft Computing, Artificial Intelligence, Data Mining, DBMS and Image Processing.Dr. G. SahooDr. G.  ...  Ram Manohar Lohia Awadh University with excellence not only in academics but also had flagship in choreography.  ... 
doi:10.5281/zenodo.4607266 fatcat:ffsh3vr6lzfpzhs5gdtjqh4yiy

Interests and Agency in AI: The case of image with Inception 3 model

Anna Sidorova
2018 Americas Conference on Information Systems  
This essay demonstrates how the agency theory and the actor-network theory (ANT) offer different, yet complementary views of the issue.  ...  Using an ethnographic mini-case study involving the application of machine learning algorithms to image classification, the essay traces interests inscribed in AI artifacts.  ...  Literature Review Artificial intelligence The term artificial intelligence was coined in "The Proposal for the Dartmouth Summer Research Project on Artificial Intelligence" where the scope of AI research  ... 
dblp:conf/amcis/Sidorova18 fatcat:m2ixl466cjendlsomypv7abj5i

MetaAID: A Flexible Framework for Developing Metaverse Applications via AI Technology and Human Editing [article]

Hongyin Zhu
2022 arXiv   pre-print
Metaverse applications may help with this task and can make many industries more interesting, more efficient, and provide a better user experience.  ...  The first challenge is that metaverse application development inevitably requires the support of various artificial intelligence (AI) technologies such as natural language processing (NLP), knowledge graph  ...  With the development of computational power and optimization algorithms, researchers can train deep and large neural network models.  ... 
arXiv:2204.01614v1 fatcat:vwvon5wuercsjjmxbef72muqie

MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning [article]

Chi-Hung Hsu, Shu-Huan Chang, Jhao-Hong Liang, Hsin-Ping Chou, Chun-Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei and Da-Cheng Juan
2018 arXiv   pre-print
when searching for neural network architectures.  ...  Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures.  ...  Introduction Convolutional Neural Networks (CNN) have shown impressive successes in computer-vision applications; however, designing effective neural networks heavily relies on experience and expertise  ... 
arXiv:1806.10332v2 fatcat:rkdl3itlencchcivm5rmx5xwbe

ME-MD: An Effective Framework for Neural Machine Translation with Multiple Encoders and Decoders

Jinchao Zhang, Qun Liu, Jie Zhou
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
The encoder-decoder neural framework is widely employed for Neural Machine Translation (NMT) with a single encoder to represent the source sentence and a single decoder to generate target words.  ...  Experiment on Chinese-English translation task shows that our ME-MD system surpasses the state-of-the-art NMT system by 2.1 BLEU points and surpasses the phrase-based Moses by 7.38 BLEU points.  ...  Comparison with Deeper and Wider Networks We carry more experiments to investigate whether our approach achieves improvements through just making the neural network seems deeper and wider or not.  ... 
doi:10.24963/ijcai.2017/474 dblp:conf/ijcai/ZhangLZ17 fatcat:anfmumw5jbhrxcdmytl232s6se

Video Question Answering on Screencast Tutorials

Wentian Zhao, Seokhwan Kim, Ning Xu, Hailin Jin
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We also propose several baseline neural network architectures based on various aspects of video contexts from the dataset.  ...  This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software.  ...  Conference on Artificial Intelligence Comparisons of the question answering performances with different models on the test dataset.  ... 
doi:10.24963/ijcai.2020/148 dblp:conf/ijcai/ZhaoKXJ20 fatcat:jx7zrqih3rbbzmp4qw3pqhydhy

Plant leaf identification system using convolutional neural network

Amiruzzaki Taslim, Sharifah Saon, Abd Kadir Mahamad, Muladi Muladi, Wahyu Nur Hidayat
2021 Bulletin of Electrical Engineering and Informatics  
This paper proposes a leaf identification system using convolutional neural network (CNN).  ...  ResNet-50 was the architecture has been used for neural networks image classification and training the network for leaf identification.  ...  This point of view is an important element of artificial intelligence [7] , [8] and develop a strong correlation of human-machine technology.  ... 
doi:10.11591/eei.v10i6.2332 fatcat:4tdy232cybdrvfvqor5jwebadu

An Enhanced Approach for Detecting Human Age and Gender Using CNN (Convolutional Neural Network) Classifier

Sai Snehith Rachamalla
2022 International Journal for Research in Applied Science and Engineering Technology  
CONCLUSION In this Python Mini project, we learned how to determine a person's gender and age via a convulsive neural network (CNN), which receives 99.98% (women) and 99.84% (men) according to our facial  ...  This approach is appropriate for real-time processing in contexts with restricted resources that require sophisticated hardware processing.  ...  Deep underground exercises are mechanical exercises in artificial intelligence, which contains indirect or unknown neural formation or deep neural networks.  ... 
doi:10.22214/ijraset.2022.44221 fatcat:i376eofa5rcm7n5rqstgyzqbwe

Distributed Machine Learning through Heterogeneous Edge Systems

Hanpeng Hu, Dan Wang, Chuan Wu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Our testbed implementation and experiments show that ADSP outperforms existing parameter synchronization models significantly in terms of ML model convergence time, scalability and adaptability to large  ...  This paper proposes ADSP, a parameter synchronization model for distributed machine learning (ML) with heterogeneous edge systems.  ...  We train a convolutional neural network (CNN) model on the Cifar10 dataset (Krizhevsky and Hinton 2010) with 1 PS and 3 workers with heterogeneous computation capacities (time ratio to train one mini-batch  ... 
doi:10.1609/aaai.v34i05.6207 fatcat:6pw77g6cxbd4tcixkyf3mhqh2y

Montréal Wrap-Up

Sara Reese Hedberg
1995 The AI Magazine  
The conference included several complementary programs: (1) technical program (249 papers, 13 invited lectures, 2 panels, 3 conference reports), (2) tutorial program (19 tutorials), (3) workshop program  ...  Winning applications were selected because they use various AI techniques (for example, expert systems, intelligent agents, data mining, neural networks) in creative new ways to solve pressing problems  ... 
doi:10.1609/aimag.v16i4.1177 dblp:journals/aim/Hedberg95 fatcat:yo2fix4fyjadveiqnrbs4q54yi
« Previous Showing results 1 — 15 out of 838 results