Details

Autor(en) / Beteiligte

• Shukla, Vidit
• Choudhary, Shilpa
• Padmanaban, Sanjeevikumar
• Singh, Krishna Kant
• Singh, Akansha
• Sachan, Vibhav Kumar

Titel

Deep Learning in Neural Networks: An Overview

Ist Teil von

• Deep Learning in Visual Computing and Signal Processing, 2023, p.29-53

Auflage

1

Ort / Verlag

United Kingdom: CRC Press

Erscheinungsjahr

2023

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• It was only up till recent times that computer science and its were sufficient for the application in basic principles. With the in the field of artificial intelligence, the subset Deep learning is towards substantial research and advances, creating diverse We cannot consider deep learning to be an individual approach; it is a collective term which comprises fields from contrasting to be associated with the common spine-Deep learning. Basis for strong approach in deep learning lies in cognizance of the of deep learning. The implementations can be performed vastly in fields through implication of not just one but numerous algorithms achieving our goal. The architecture of deep learning has enhanced in previous years exponentially, and as per demand, the refinement of learning implying that the architecture is dynamic. A few of the most improvised architectures are mentioned below: 30Recurrent neural networks (RNNs) Long short-term memory (LSTM)/gated recurrent unit (GRU) Convolutional neural networks (CNNs) Deep belief networks (DBN) and deep stacking networks (DSNs) Open source software options for deep learning. The area of implementation for deep learning in problem solving is vast. Feed forward networks are very effective as well as recurrent networks can be a good source for the solution of the deep learning problems. The Framework for deep learning can be implemented in software packages for the useful creation of neural network. The framework needs an implementation on a standardized scale and hence needs industrial experts for the framework to be implemented. The entire framework is in simple terms based on the Diagnosis of the problem and further, evaluating the problem. It is evident that the architecture and framework of deep learning is vast and expanding its horizons to every field possible for implementation. Therefore deep learning architecture and framework would be vitalized, with step by step conception. The architecture would be simplified as well as illustrated. All the aforesaid architecture like Recurrent neural network, Long short term memory/gated recurrent unit, convolutional, Deep belief-deep stack as well as open source would be simplified as well as illustrated. The framework for deep learning can be implemented in software packages for the useful creation of neural network. The modern deep learning models are a result of common neural networks that are used in variable layers. Neural network plays a major role being an integral part of deep learning layers. It is the basis for creation of the layers in the method for deep learning. The deep learning mechanism learned much by the neural networks speech recognition system, which was known as long short-term memory network; this is a type of neural network recurrent in nature, which was proposed and introduced by Hochreiter and Schmidhuber in early 1997. With time, the developments increased and the deep leaning and neural networks gained higher preference for speech recognition, after Google improvised the method in speech recognition. This led to hardware association of deep learning as well. More advancement in hardware has made the deep learning process important.