Demystifying Deep Learning: Developing and Evaluating a User-Centered Learning App for Beginners to Gain Practical Experience

i-com ◽  
2020 ◽  
Vol 19 (3) ◽  
pp. 201-213
Author(s):  
Sven Schultze ◽  
Uwe Gruenefeld ◽  
Susanne Boll
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Practical Experience ◽  
Learning Problems ◽  
User Evaluation ◽  
Classification Problems ◽  
Human Centered Design ◽  
Technical Evaluation ◽  
Programming Skills ◽  
Barrier To Entry

Abstract Deep Learning has revolutionized Machine Learning, enhancing our ability to solve complex computational problems. From image classification to speech recognition, the technology can be beneficial in a broad range of scenarios. However, the barrier to entry is quite high, especially when programming skills are missing. In this paper, we present the development of a learning application that is easy to use, yet powerful enough to solve practical Deep Learning problems. We followed the human-centered design approach and conducted a technical evaluation to identify solvable classification problems. Afterwards, we conducted an online user evaluation to gain insights on users’ experience with the app, and to understand positive as well as negative aspects of our implemented concept. Our results show that participants liked using the app and found it useful, especially for beginners. Nonetheless, future iterations of the learning app should step-wise include more features to support advancing users.

scholarly journals Machine learning for human learners: opportunities, issues, tensions and threats

2020 ◽  
Author(s):  
Mary E. Webb ◽  
Andrew Fluck ◽  
Johannes Magenheim ◽  
Joyce Malyn-Smith ◽  
Juliet Waters ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Ethical Issues ◽  
Practical Experience ◽  
Learning Systems ◽  
Learning System ◽  
Adaptive Behaviour ◽  
Recent Developments ◽  
Key Aspects ◽  
School Curricula

AbstractMachine learning systems are infiltrating our lives and are beginning to become important in our education systems. This article, developed from a synthesis and analysis of previous research, examines the implications of recent developments in machine learning for human learners and learning. In this article we first compare deep learning in computers and humans to examine their similarities and differences. Deep learning is identified as a sub-set of machine learning, which is itself a component of artificial intelligence. Deep learning often depends on backwards propagation in weighted neural networks, so is non-deterministic—the system adapts and changes through practical experience or training. This adaptive behaviour predicates the need for explainability and accountability in such systems. Accountability is the reverse of explainability. Explainability flows through the system from inputs to output (decision) whereas accountability flows backwards, from a decision to the person taking responsibility for it. Both explainability and accountability should be incorporated in machine learning system design from the outset to meet social, ethical and legislative requirements. For students to be able to understand the nature of the systems that may be supporting their own learning as well as to act as responsible citizens in contemplating the ethical issues that machine learning raises, they need to understand key aspects of machine learning systems and have opportunities to adapt and create such systems. Therefore, some changes are needed to school curricula. The article concludes with recommendations about machine learning for teachers, students, policymakers, developers and researchers.

scholarly journals Web Service for Point Cloud Supported Robot Programming Using Machine Learning

2022 ◽  
pp. 253-262
Author(s):  
Kristina Enes
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Web Service ◽  
Production System ◽  
Production Line ◽  
Robot Programming ◽  
Programming Skills ◽  
Image Processing Algorithms ◽  
Processing Algorithms

AbstractIn industrial automation, the use of robots is already standard. But there is still a lot of room for further automation. One such place where improvements can be made is in the adjustment of a production system to new and unknown products. Currently, this task includes the reprogramming of the robot and a readjustment of the image processing algorithms if sensors are involved. This takes time, effort, and a specialist, something especially small and middle-sized companies shy away from. We propose to represent a physical production line with a digital twin, using the simulated production system to generate labeled data to be used for training in a deep learning component. An artificial neural network will be trained to both recognize and localize the observed products. This allows the production line to handle both known and unknown products more flexible. The deep learning component itself is located in a cloud and can be accessed through a web service, allowing any member of the staff to initiate the training, regardless of their programming skills. In summary, our approach addresses not only further automation in manufacturing but also the use of synthesized data for deep learning.

scholarly journals Deep learning models for classification of gases detected by sensor arrays of artificial nose

2019 ◽  
Author(s):  
Ismael Araujo ◽  
Juan Gamboa ◽  
Adenilton Silva
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Sensor Arrays ◽  
Machine Learning Algorithms ◽  
Human Beings ◽  
Learning Models ◽  
Classification Problems ◽  
Artificial Nose ◽  
Learning Techniques

To recognize patterns that are usually imperceptible by human beings has been one of the main advantages of using machine learning algorithms The use of Deep Learning techniques has been promising to the classification problems, especially the ones related to image classification. The classification of gases detected by an artificial nose is one other area where Deep Learning techniques can be used to seek classification improvements. Succeeding in a classification task can result in many advantages to quality control, as well as to preventing accidents. In this work, it is presented some Deep Learning models specifically created to the task of gas classification.

scholarly journals Deep Ordinal Regression Based on Data Relationship for Small Datasets

2017 ◽  
Author(s):  
Yanzhu Liu ◽  
Adams Wai Kin Kong ◽  
Chi Keong Goh
Keyword(s):  
Deep Learning ◽  
Deep Neural Networks ◽  
Color Image ◽  
Binary Classification ◽  
Ordinal Regression ◽  
Learning Problems ◽  
Classification Problems ◽  
Regression Problem ◽  
New Approach ◽  
High Level

Ordinal regression aims to classify instances into ordinal categories. As with other supervised learning problems, learning an effective deep ordinal model from a small dataset is challenging. This paper proposes a new approach which transforms the ordinal regression problem to binary classification problems and uses triplets with instances from different categories to train deep neural networks such that high-level features describing their ordinal relationship can be extracted automatically. In the testing phase, triplets are formed by a testing instance and other instances with known ranks. A decoder is designed to estimate the rank of the testing instance based on the outputs of the network. Because of the data argumentation by permutation, deep learning can work for ordinal regression even on small datasets. Experimental results on the historical color image benchmark and MSRA image search datasets demonstrate that the proposed algorithm outperforms the traditional deep learning approach and is comparable with other state-of-the-art methods, which are highly based on prior knowledge to design effective features.

scholarly journals Classification of Big Data: Machine Learning Problems and Challenges in Network Intrusion Prediction

2018 ◽  
Vol 7 (4.36) ◽  
pp. 1189
Author(s):  
Yasser Mohammad Al-Sharo ◽  
Ghazi Shakah ◽  
Mutasem Sh.Alkhaswneh ◽  
Bajes Zeyad Aljunaeidi ◽  
Malik Bader Alazzam
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Representation Learning ◽  
Learning Problems ◽  
Traffic Information ◽  
Classification Problems ◽  
Network Intrusion ◽  
Learning Techniques ◽  
Geometric Techniques

Centre of attraction of paper is on the main complication on classification of Big Data on network encroachment on traffic. It also explains the disputes this system faces that is bestowed by the Big Data difficulties that are correlate with the network interruption forecast. Forecasting of an attainable interruption in a network entails a prolonged accumulation of traffic information or data and being able to get the concept on their features on motion. The constant accumulation in the network of traffic data thereafter ends with Big Data difficulties that as a result of the large amount, change and possessions of Big Data. In order to learn the features of a network, one needs to have the skills in the machine techniques that are always able to capture world skills and knowledge of the traffic to be in order. The properties of Big Data will always end to an important system disputes to be able to apply machine learning foundation. The paper also discusses the disputes and problems in the way of taking care of Big Data categorization representing geometric techniques of learning along with the existing technologies of Big networking. The study particularly explains challenges that have a relationship with the combined directed by the techniques one learns, machine long learning techniques, and representation-learning techniques and technologies that are related to Big Data for example Hive, Hadoop and Cloud that are basics that enhances problem-solving that gives relevant solutions to classification problems in traffic networking.  

scholarly journals Handwritten Character Recognition using Deep Learning

2020 ◽  
Vol 8 (6) ◽  
pp. 5815-5819
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Language Processing ◽  
Character Recognition ◽  
Human Life ◽  
General Purpose ◽  
Learning Problems ◽  
Handwritten Character Recognition ◽  
Handwritten Documents ◽  
Handwritten Character

In day to day human life, handwritten documents are a general purpose for communication and restoring their information. In the field of computer science, character recognition using Deep Learning has more attention. DL has a massive set of pattern recognition tools that can apply to speech recognition, image processing, natural language processing and has a remarkable capability to find out a solution for complex machine learning problems. DL can focus on the specific feature of an image to character recognition for enhancing efficiency and accuracy. In this paper, we have presented a methods for handwritten character recognition using deep learning.

scholarly journals A FULLY AUTOMATED PIPELINE FOR CLASSIFICATION TASKS WITH AN APPLICATION TO REMOTE SENSING

2016 ◽  
Vol XLI-B3 ◽  
pp. 923-929
Author(s):  
K. Suzuki ◽  
M. Claesen ◽  
H. Takeda ◽  
B. De Moor
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Object Recognition ◽  
Character Recognition ◽  
Domain Knowledge ◽  
High Performance ◽  
A Priori ◽  
Training Data ◽  
Classification Problems

Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed ‘shallow’ machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

scholarly journals Building and Improving Artificial Neural Network Classifier

2019 ◽  
Vol 8 (9) ◽  
pp. 2742-2747
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Deep Learning ◽  
Cross Validation ◽  
Parameter Tuning ◽  
Classification Problems ◽  
Artificial Neural Network Classifier ◽  
Artificial Neural

Deep learning is a spectrum of machine learning which uses advanced neural networks to solve the various machine learning problems. Its working is very similar to the working of a human brain where the models take decision based on various input parameters. There are multiple open source libraries which implement neural networks, like Tensorflow, Theano, PyTorch, Keras etc. In this paper we have proposed a generic architecture that can be used for any type of classification problems with binary output or classification output using Deep Learning model: Artificial Neural Network (ANN). In the architectural model after Data preprocessing we first build the ANN classifier using Keras library with Tensorflow backends, second step we have apply Cross-validation method for better accuracy. Then we perform Dropout Regularization method for preventing from overfitting and at last we have applied grid search technique for parameter tuning that basically will test several combinations of Hyperparameter values and will eventually return the best selection choice with K-Fold cross validation. And the experimental results shows in higher accuracy with ours proposed architecture and in our proposed architecture results we remove the randomness from the model. In the proposed architecture we can again rebuild developing our model using Keras Callback function by using this feature in our model it does not create any major difference in terms of accuracy. But as we know the accuracy will vary with parameter tuning. The main advantage of using Keras Callback function method is it’s saves a lot of time for building model and it is easy for debugging the model.

scholarly journals A Deep Belief Network Classification Approach for Automatic Diacritization of Arabic Text

2021 ◽  
Vol 11 (11) ◽  
pp. 5228
Author(s):  
Waref Almanaseer ◽  
Mohammad Alshraideh ◽  
Omar Alkadi
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Language Processing ◽  
High Accuracy ◽  
Deep Belief Network ◽  
Learning Problems ◽  
Arabic Text ◽  
Belief Network ◽  
Benchmark Datasets ◽  
Learning Research

Deep learning has emerged as a new area of machine learning research. It is an approach that can learn features and hierarchical representation purely from data and has been successfully applied to several fields such as images, sounds, text and motion. The techniques developed from deep learning research have already been impacting the research on Natural Language Processing (NLP). Arabic diacritics are vital components of Arabic text that remove ambiguity from words and reinforce the meaning of the text. In this paper, a Deep Belief Network (DBN) is used as a diacritizer for Arabic text. DBN is an algorithm among deep learning that has recently proved to be very effective for a variety of machine learning problems. We evaluate the use of DBNs as classifiers in automatic Arabic text diacritization. The DBN was trained to individually classify each input letter with the corresponding diacritized version. Experiments were conducted using two benchmark datasets, the LDC ATB3 and Tashkeela. Our best settings achieve a DER and WER of 2.21% and 6.73%, receptively, on the ATB3 benchmark with an improvement of 26% over the best published results. On the Tashkeela benchmark, our system continues to achieve high accuracy with a DER of 1.79% and 14% improvement.

scholarly journals A FULLY AUTOMATED PIPELINE FOR CLASSIFICATION TASKS WITH AN APPLICATION TO REMOTE SENSING

2016 ◽  
Vol XLI-B3 ◽  
pp. 923-929
Author(s):  
K. Suzuki ◽  
M. Claesen ◽  
H. Takeda ◽  
B. De Moor
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Object Recognition ◽  
Character Recognition ◽  
Domain Knowledge ◽  
High Performance ◽  
A Priori ◽  
Training Data ◽  
Classification Problems

Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed ‘shallow’ machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

Sign in / Sign up

Export Citation Format

Share Document