scholarly journals An Overview Studying of Deep Learning

2020 ◽  
pp. 394-398
Author(s):  
Mya Sandar Kyin ◽  
Zaw Lin Oo ◽  
Khin Mar Cho
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Computational Models ◽  
Unstructured Data ◽  
Levels Of Abstraction ◽  
Large Numbers ◽  
Multiple Levels ◽  
Multiple Processing

Deep learning is a subfield of machine learning however both drop under the broad category of artificial intelligence. Deep learning is what powers the most human-like artificial intelligence that consents computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. Deep learning is making major advances in solving problems hence categorized in wider section of artificial intelligence. The main advantage of Deep Learning is to create an artificial neural network that can learn and make intelligent decisions on its own and to process large numbers of features makes deep learning very powerful when dealing with unstructured data.

scholarly journals Aspect Based Sentimen Analysis Opini Publik Pada Instagram dengan Convolutional Neural Network

2019 ◽  
Vol 1 (2) ◽  
pp. 50-57
Author(s):  
Muhammad Arief Rahman ◽  
Herman Budianto ◽  
Esther Irawati Setiawan
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network

Internet sebagai sarana informasi dan komunikasi sudah sangat dikenal di kalangan masyarakat dalam menawarkan kemudahan dan fleksibilitas yang cukup memadai ketika menjadi media. Oleh karena itu opini publik terhadap Operator Telekomunikasi merupakan hal yang sangat penting untuk dijadikan patokan. Namun, untuk mengevaluasi umpan balik online itu, bukan masalah sederhana. Kadang-kadang ketika menganalisis ulasan online yang berkembang pesat ini, menjadi sulit untuk mengkategorikan apakah opini pelanggan puas atau tidak puas terhadap produk dan layanan. Selain itu, sebagai bagian dari peningkatan kualitas mereka, organisasi seperti jasa ini perlu mengklasifikasikan aspek produk dan layanan yang paling disukai pelanggan. Deep Learning adalah area baru dalam penelitian Machine Learning, yang telah diperkenalkan dengan tujuan menggerakkan Machine Learning lebih dekat dengan salah satu tujuan aslinya yaitu Artificial Intelligence. Deep Learning adalah tentang belajar beberapa tingkat representasi dan abstraksi yang membantu untuk memahami data seperti gambar, suara, dan teks. Convolutional Neural Network adalah salah satu contoh metode Deep Learning. Metode Convolutional Neural Network diharapkan dapat digunakan dalam pengimplementasian opini publik untuk keperluan data training yang dikumpulkan dari beragam data yang dianotasikan kelas sentimennya secara otomatis. Hasil dari penelitian menunjukkan dari 4 aspek dan 3 sentimen maka didapatkan nilai rata-rata precision, recall, dan f1-score adalah precision  97.6%, recall 84%, f1-score 90.3%. Bisa disimpulkan score representation ini dapat digunakan untuk klasifikasi sentimen.

scholarly journals A Practical Tutorial on Graph Neural Networks

2022 ◽  
Author(s):  
Isaac Ronald Ward ◽  
Jack Joyner ◽  
Casey Lickfold ◽  
Yulan Guo ◽  
Mohammed Bennamoun
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Input Data ◽  
Unstructured Data ◽  
Data Types ◽  
Learning Techniques ◽  
Graph Neural Networks ◽  
Unique Ability

Graph neural networks (GNNs) have recently grown in popularity in the field of artificial intelligence (AI) due to their unique ability to ingest relatively unstructured data types as input data. Although some elements of the GNN architecture are conceptually similar in operation to traditional neural networks (and neural network variants), other elements represent a departure from traditional deep learning techniques. This tutorial exposes the power and novelty of GNNs to AI practitioners by collating and presenting details regarding the motivations, concepts, mathematics, and applications of the most common and performant variants of GNNs. Importantly, we present this tutorial concisely, alongside practical examples, thus providing a practical and accessible tutorial on the topic of GNNs.

scholarly journals Introduction to the TPLP Special Issue on User-oriented Logic Programming and Reasoning Paradigms

2019 ◽  
Vol 19 (2) ◽  
pp. 109-113
Author(s):  
STEFAN ELLMAUTHALER ◽  
CLAUDIA SCHULZ
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Knowledge Representation ◽  
Logic Programming ◽  
Unstructured Data ◽  
Knowledge Representation And Reasoning ◽  
Special Issue

With the rise of machine learning, and more recently the overwhelming interest in deep learning, knowledge representation and reasoning (KRR) approaches struggle to maintain their position within the wider Artificial Intelligence (AI) community. Often considered as part of thegood old-fashioned AI(Haugeland 1985) – like a memory of glorious old days that have come to an end – many consider KRR as no longer applicable (on its own) to the problems faced by AI today (Blackwell 2015; Garneloet al.2016). What they see are logical languages with symbols incomprehensible by most, inference mechanisms that even experts have difficulties tracing and debugging, and the incapability to process unstructured data like text.

scholarly journals Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

2021 ◽  
Vol 2 ◽  
Author(s):  
Danshi Wang ◽  
Min Zhang
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Optical Communication ◽  
Optical Communications ◽  
Channel Modeling ◽  
Modeling Method ◽  
Learning Performance ◽  
Sequential Data

Techniques from artificial intelligence have been widely applied in optical communication and networks, evolving from early machine learning (ML) to the recent deep learning (DL). This paper focuses on state-of-the-art DL algorithms and aims to highlight the contributions of DL to optical communications. Considering the characteristics of different DL algorithms and data types, we review multiple DL-enabled solutions to optical communication. First, a convolutional neural network (CNN) is used for image recognition and a recurrent neural network (RNN) is applied for sequential data analysis. A variety of functions can be achieved by the corresponding DL algorithms through processing the different image data and sequential data collected from optical communication. A data-driven channel modeling method is also proposed to replace the conventional block-based modeling method and improve the end-to-end learning performance. Additionally, a generative adversarial network (GAN) is introduced for data augmentation to expand the training dataset from rare experimental data. Finally, deep reinforcement learning (DRL) is applied to perform self-configuration and adaptive allocation for optical networks.

scholarly journals PENGKLASIFIKASIAN GENRE MUSIK INDONESIA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

Sebatik ◽  
2021 ◽  
Vol 25 (1) ◽  
Author(s):  
Carl Ray Wairata ◽  
Ericks Rachmat Swedia ◽  
Margi Cahyanti
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network

Pada zaman sekarang sudah terdapat banyak sekali teknologi Artificial Intelligence. Artificial Intelligence sendiri memiliki beberapa sub bab, salah satunya adalah Machine Learning dan Deep Learning merupakan salah sub bab dari Machine Learning itu sendiri. Convolutional Neural network (CNN) adalah salah satu jenis neural network yang biasa digunakan pada data gambar. Pada penelitian ini akan digunakan untuk mengklasifikasikan genre musik dengan cara mengonversi data pada lagu menjadi sebuah gambar yang kita sebut spektogram. Pada penelitian akan mengimplementasikan CNN dalam mengategorikan 3 genre musik di Indonesia yakni; dangdut, Jazz dan Pop. Pada penelitian ini terdapat 100 lagu untuk masing-masing genre sebagai data setnya. Tujuan dari penelitian ini sendiri adalah mengoptimalkan tingkat akurasi dalam pengategorian genre musik menggunakan model CNN. Berdasarkan penelitian yang sudah dilakukan didapatkan bahwa penggunaan 35 epoch memiliki tingkat akurasi yang optimal yakni; tingkat akurasi tes sebesar 81,33% dan tingkat akurasi validasi sebesar 100%. Implementasi ini diharapkan dapat menentukan kategori dalam musik.

scholarly journals High-Performance Deep learning to Detection and Tracking Tomato Plant Leaf Predict Disease and Expert Systems

2021 ◽  
Vol 10 (2) ◽  
Author(s):  
Yaser AbdulAali Jasim
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
High Performance ◽  
Plant Disease ◽  
Detection System ◽  
Open Data ◽  
Data Set ◽  
Performance Rate

Nowadays, technology and computer science are rapidly developing many tools and algorithms, especially in the field of artificial intelligence.  Machine learning is involved in the development of new methodologies and models that have become a novel machine learning area of applications for artificial intelligence. In addition to the architectures of conventional neural network methodologies, deep learning refers to the use of artificial neural network architectures which include multiple processing layers. In this paper, models of the Convolutional neural network were designed to detect (diagnose) plant disorders by applying samples of healthy and unhealthy plant images analyzed by means of methods of deep learning. The models were trained using an open data set containing (18,000) images of ten different plants, including healthy plants. Several model architectures have been trained to achieve the best performance of (97 percent) when the respectively [plant, disease] paired are detected. This is a very useful information or early warning technique and a method that can be further improved with the substantially high-performance rate to support an automated plant disease detection system to work in actual farm conditions.

Deep Learning in Computational Neuroscience

2020 ◽  
pp. 43-63
Author(s):  
Sanjay Saxena ◽  
Sudip Paul ◽  
Adhesh Garg ◽  
Angana Saikia ◽  
Amitava Datta
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Human Brain ◽  
Convolutional Neural Network ◽  
Computational Neuroscience ◽  
Deep Model ◽  
The World ◽  
Current Scenario

Computational neuroscience is inspired by the mechanism of the human brain. Neural networks have reformed machine learning and artificial intelligence. Deep learning is a type of machine learning that teaches computers to do what comes naturally to individuals: acquire by example. It is inspired by biological brains and became the essential class of models in the field of machine learning. Deep learning involves several layers of computation. In the current scenario, researchers and scientists around the world are focusing on the implementation of different deep models and architectures. This chapter consists the information about major architectures of deep network. That will give the information about convolutional neural network, recurrent neural network, multilayer perceptron, and many more. Further, it discusses CNN (convolutional neural network) and its different pretrained models due to its major requirements in visual imaginary. This chapter also deliberates about the similarity of deep model and architectures with the human brain.

scholarly journals Machine Learning Versus Deep Learning Performances on the Sentiment Analysis of Product Reviews

2021 ◽  
Vol 11 (2) ◽  
pp. 103-109
Author(s):  
Pumrapee Poomka ◽  
◽  
Nittaya Kerdprasop ◽  
Kittisak Kerdprasop
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Computational Models ◽  
Shopping Mall ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Product Reviews ◽  
Review Section

At this current digital era, business platforms have been drastically shifted toward online stores on internet. With the internet-based platform, customers can order goods easily using their smart phones and get delivery at their place without going to the shopping mall. However, the drawback of this business platform is that customers do not really know about the quality of the products they ordered. Therefore, such platform service often provides the review section to let previous customers leave a review about the received product. The reviews are a good source to analyze customer's satisfaction. Business owners can assess review trend as either positive or negative based on a feedback score that customers had given, but it takes too much time for human to analyze this data. In this research, we develop computational models using machine learning techniques to classify product reviews as positive or negative based on the sentiment analysis. In our experiments, we use the book review data from amazon.com to develop the models. For a machine learning based strategy, the data had been transformed with the bag of word technique before developing models using logistic regression, naïve bayes, support vector machine, and neural network algorithms. For a deep learning strategy, the word embedding is a technique that we used to transform data before applying the long short-term memory and gated recurrent unit techniques. On comparing performance of machine learning against deep learning models, we compare results from the two methods with both the preprocessed dataset and the non-preprocessed dataset. The result is that the bag of words with neural network outperforms other techniques on both non-preprocess and preprocess datasets.

scholarly journals Deep Learning Machine using Hierarchical Cluster Features

2019 ◽  
Vol 29 (3) ◽  
pp. 82
Author(s):  
Sara Salman ◽  
Jamila H. Soud
Keyword(s):  
Deep Learning ◽  
Computational Models ◽  
Hierarchical Cluster ◽  
Data Representation ◽  
Cluster Method ◽  
Classification Problems ◽  
Levels Of Abstraction ◽  
Image Translation ◽  
Multiple Levels ◽  
Learning Machine

Deep learning of multi-layer computational models allowed processing to recognize data representation at multiple levels of abstraction. These techniques have greatly improved the latest ear recognition technology. PNN is a type of radiative basis for classification problems and is based on the Bayes decision-making base, which reduces the expected error of classification. In this paper, strong features of images are used to give a good result, therefore, SIFT method using these features after adding improvements and developments. This method was one of the powerful algorithms in matching that needed to find energy pixels. This method gives stronger feature on features and gives a large number of a strong pixel, which is considered a center and neglected the remainder of it in our work. Each pixel of which is constant for image translation, scaling, rotation, and embedded lighting changes in lighting or 3D projection. Therefore, the interpretation is developed by using a hierarchical cluster method; to assign a set of properties (find the approximation between pixels) were classified into one.

The Impact of Deep Learning on the Semantic Machine Learning Representation

2021 ◽  
pp. 22-49
Author(s):  
Abdul Kader Saiod ◽  
Darelle van Greunen
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Big Data ◽  
Deep Learning ◽  
Heterogeneous Data ◽  
Levels Of Abstraction ◽  
Knowledge Based ◽  
Data Representations ◽  
High Level ◽  
The Impact

Deep learning (DL) is one of the core subsets of the semantic machine learning representations (SMLR) that impact on discovering multiple processing layers of non-linear big data (BD) transformations with high levels of abstraction concepts. The SMLR can unravel the concealed explanation characteristics and modifications of the heterogeneous data sources that are intertwined for further artificial intelligence (AI) implementations. Deep learning impacts high-level abstractions in data by deploying hierarchical architectures. It is practically challenging to model big data representations, which impacts on data and knowledge-based representations. Encouraged by deep learning, the formal knowledge representation has the potential to influence the SMLR process. Deep learning architecture is capable of modelling efficient big data representations for further artificial intelligence and SMLR tasks. This chapter focuses on how deep learning impacts on defining deep transfer learning, category, and works based on the techniques used on semantic machine learning representations.

Sign in / Sign up

Export Citation Format

Share Document