Proceedings Article10.1109/IECBES.2016.7843542
A review on optimization algorithm for deep learning method in bioinformatics field
Siti Noorain Mohmad Yousoff,Amirah Baharin,Afnizanfaizal Abdullah +2 more
- 01 Dec 2016
- Vol. 2016, pp 707-711
16
TL;DR: A global optimization technique such as differential search algorithm can be used to assist deep learning method in order to get best finding result and data.
read more
Abstract: In the past few years, deep learning has been used widely in bioinformatics area to solve common problems such as protein sequence prediction, phylogenic inferences, multiple sequence alignment and many more. It has been in the spotlight as a powerful approach which makes significant advances in taking care of the issues that haunt artificial intelligence community for many years. However, several weaknesses such as trap at local minima, lower performance and high computational time still occur in deep learning. Therefore, global optimization technique such as differential search algorithm can be used to assist deep learning method in order to get best finding result and data. This review will cover fundamental of deep learning and their involvement in bioinformatics field as well as implementation of differential search algorithm and their involvement in bioinformatics field.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
State-of-the-Art CNN Optimizer for Brain Tumor Segmentation in Magnetic Resonance Images.
Muhammad Yaqub,Feng Jinchao,M. Sultan Zia,Kaleem Arshid,Kebin Jia,Zaka Ur Rehman,Atif Mehmood +6 more
TL;DR: A comparative analysis of 10 different state-of-the-art gradient descent-based optimizers of CNN, namely Adaptive Gradient (Adagrad), Adaptive Delta (AdaDelta), Stochastic Gradient Descent (SGD),adaptive Momentum (Adam), Cyclic Learning Rate (CLR), Adaptives Max Pooling (Adamax), Root Mean Square Propagation (RMS Prop), Nesterov AdaptiveMomentum (Nadam),
182
Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations.
TL;DR: This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL.
156
An Experimental Approach towards the Performance Assessment of Various Optimizers on Convolutional Neural Network
S. Vani,T. V. Madhusudhana Rao +1 more
- 23 Apr 2019
TL;DR: Seven optimizers namely Stochastic Gradient Descent (SGD), RMSProp, Adam, Adamax, Adagrad, Adadelta, and Nadam are implemented in CNN on Indian Pines Dataset and accuracy comparison results are shown graphically where Adamax outperforms with 99.58% accuracy.
104
Temperature guided network for 3D joint segmentation of the pancreas and tumors
TL;DR: Wang et al. as mentioned in this paper proposed a 3D fully convolutional neural network with three temperature guided modules, namely, balance temperature loss, rigid temperature optimizer and soft temperature indictor, to realize joint segmentation of the pancreas and tumors.
18
A robust optimized convolutional neural network model for human activity recognition using sensing devices
TL;DR: A robust (CNN) deep learning model has been built up and proposed in order to enhance the recognition precision of human activities and shows that the precision has achieved 97.5% with respect to the NAdam optimizer which would be considered as the most effectively recognizer compared to other deep learning architectures.
7
References
•Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Deep learning in neural networks
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
18.7K
Representation Learning: A Review and New Perspectives
TL;DR: Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
•Book
Learning Deep Architectures for AI
Yoshua Bengio
- 01 Jan 2009
TL;DR: The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.