What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
Tarek M. Taha mainly focuses on Memristor, Artificial neural network, Convolutional neural network, Artificial intelligence and Deep learning.
His Memristor research includes themes of Neuromorphic engineering, Electronic circuit and Crossbar switch.
The study incorporates disciplines such as Theoretical computer science, Computer engineering and Memistor in addition to Crossbar switch.
His specific area of interest is Artificial neural network, where Tarek M. Taha studies Deep belief network.
His research investigates the link between Convolutional neural network and topics such as Contextual image classification that cross with problems in Feature and Benchmark.
His work carried out in the field of Artificial intelligence brings together such families of science as Residual and Pattern recognition.
His most cited work include:
- Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation. (277 citations)
- A State-of-the-Art Survey on Deep Learning Theory and Architectures (260 citations)
- The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches. (208 citations)
What are the main themes of his work throughout his whole career to date?
Tarek M. Taha mainly focuses on Memristor, Artificial intelligence, Neuromorphic engineering, Artificial neural network and Crossbar switch.
Tarek M. Taha combines subjects such as Spice, Electronic circuit and Resistive random-access memory, Memistor with his study of Memristor.
Tarek M. Taha has included themes like Machine learning, Residual and Pattern recognition in his Artificial intelligence study.
The Neuromorphic engineering study combines topics in areas such as Electrical engineering, Voltage, Intrusion detection system and Spiking neural network.
Tarek M. Taha has researched Artificial neural network in several fields, including Computer architecture, Computer engineering and Parallel computing.
His biological study deals with issues like Recurrent neural network, which deal with fields such as Machine translation.
He most often published in these fields:
- Memristor (39.61%)
- Artificial intelligence (38.96%)
- Neuromorphic engineering (35.06%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (38.96%)
- Deep learning (23.38%)
- Pattern recognition (20.13%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Deep learning, Pattern recognition, Convolutional neural network and Neuromorphic engineering.
His research integrates issues of Machine learning and Residual in his study of Artificial intelligence.
His Deep learning study integrates concerns from other disciplines, such as Pixel, Computer vision, Oncology and Reinforcement learning.
His study in the field of Support vector machine also crosses realms of Field.
His Convolutional neural network study incorporates themes from Cognitive neuroscience of visual object recognition, Contextual image classification, Benchmark, Transfer of learning and Efficient energy use.
Neuromorphic engineering is the subject of his research, which falls under Artificial neural network.
Between 2018 and 2021, his most popular works were:
- A State-of-the-Art Survey on Deep Learning Theory and Architectures (260 citations)
- Recurrent residual U-Net for medical image segmentation (68 citations)
- Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network (57 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Central processing unit
His primary areas of study are Artificial intelligence, Convolutional neural network, Pattern recognition, Deep learning and Residual.
His research on Pattern recognition focuses in particular on Segmentation.
His studies deal with areas such as Transfer of learning, Machine translation and Reinforcement learning as well as Deep learning.
His Transfer of learning research is multidisciplinary, incorporating perspectives in Artificial neural network, Recurrent neural network and Network model.
His study in Residual is interdisciplinary in nature, drawing from both Cognitive neuroscience of visual object recognition and Medical imaging.
As a member of one scientific family, Tarek M. Taha mostly works in the field of Benchmark, focusing on Image segmentation and, on occasion, Contextual image classification.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
