8 results ·
● Live web index
T
techscience.com
article
https://www.techscience.com/cmc/special_detail/neural_networks
Home / Journals / CMC / Special Issue / Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges. # Advances in Deep Learning and Neural Networks: Architectures, Applications, and Challenges. **Email:** dkkang@dongseo.ac.kr. **Affiliation:** Department of Computer Engineering, Dongseo University, Busan, 47011, South Korea. **Research Interests:** Adversarial Machine Learning, Generative Models, Deep Reinforcement Learning, Hyperparameter Optimization and Network Architecture Search, Multi-Agent Reinforcement Learning, Bankruptcy prediction models and financial ratio analysis, Datamining based intrusion detection. Deep learning and neural networks have revolutionized various fields, including computer vision, natural language processing, and healthcare. This special issue aims to gather innovative research contributions that highlight significant progress and practical implementations of deep learning and neural networks. - Novel neural network architectures (e.g., CNNs, RNNs, GANs, Transformers). - Addressing bias and fairness in deep learning models. - Emerging trends and future challenges in deep learning research. - Interdisciplinary approaches combining deep learning with other fields. Deep Learning, Neural Networks, Transformers, Large Language Models.
D
developer.nvidia.com
article
https://developer.nvidia.com/blog/deep-learning-nutshell-history-training/
The main hurdle at this point was to train big, deep networks, which suffered from the vanishing gradient problem, where features in early layers could not be learned because no learning signal reached these layers. Additional material: Deep Learning in Neural Networks: An Overview. Backpropagation of errors, or often simply backpropagation, is a method for finding the gradient of the error with respect to weights over a neural network. Figure 1: Backpropagation for an arbitrary layer in a deep neural network. Figure 1: Backpropagation for an arbitrary layer in a deep neural network. We can imagine a forward pass in which a matrix (dimensions: number of examples x number of input nodes) is input to the network and propagated t through it, where we always have the order (1) input nodes, (2) weight matrix (dimensions: input nodes x output nodes), and (3) output nodes, which usually also have a non-linear activation function (dimensions: examples x output nodes). ### Accelerate Machine Learning with the cuDNN Deep Neural Network Library.
M
medium.com
article
https://medium.com/@esthon/the-rise-of-neural-networks-unlocking-the-power-of…
# The Rise of Neural Networks: Unlocking the Power of Deep Learning | by Esthon Medeiros Jr | Medium. # The Rise of Neural Networks: Unlocking the Power of Deep Learning. Today, thanks to neural networks and deep learning, it's a reality. This article walks you through the evolution of machine learning, the emergence of neural networks, and how deep learning is transforming industries. Neural networks are the foundation of modern deep learning systems. Enter deep learning—a paradigm that uses networks with many hidden layers, enabling the learning of intricate patterns in high-dimensional data. ## From Neural Networks to Deep Learning. Deep learning architectures, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), go beyond the basic feedforward structure. Companies like Google, Amazon, and Tesla rely heavily on deep learning models to power search engines, recommendation systems, and self-driving technology. Neural networks and deep learning have transformed artificial intelligence from a niche academic discipline into a driving force of innovation.
E
eajournals.org
research
https://eajournals.org/wp-content/uploads/sites/21/2025/05/The-Rise-of-Deep-L…
Neural networks, the European Journal of Computer Science and Information Technology,13(17),88-98, 2025 Print ISSN: 2054-0957 (Print) Online ISSN: 2054-0965 (Online) Website: https://www.eajournals.org/ Publication of the European Centre for Research Training and Development -UK 89 cornerstone of deep learning, have shown exceptional performance in tasks such as image and speech recognition, natural language processing, and autonomous decision-making. European Journal of Computer Science and Information Technology,13(17),88-98, 2025 Print ISSN: 2054-0957 (Print) Online ISSN: 2054-0965 (Online) Website: https://www.eajournals.org/ Publication of the European Centre for Research Training and Development -UK 94 Reinforcement Learning The integration of deep learning with reinforcement learning has led to significant breakthroughs in AI capabilities: Deep Reinforcement Learning: Researchers have achieved remarkable results in complex decision-making tasks by combining deep neural networks with reinforcement learning. Fig. 2: Quantitative Impacts of Deep Learning Advancements in AI Research [3, 6] European Journal of Computer Science and Information Technology,13(17),88-98, 2025 Print ISSN: 2054-0957 (Print) Online ISSN: 2054-0965 (Online) Website: https://www.eajournals.org/ Publication of the European Centre for Research Training and Development -UK 96 Future Prospects As computational resources continue to expand and datasets grow larger, the potential for deep learning and neural networks in AI is boundless.
P
pub.towardsai.net
article
https://pub.towardsai.net/deep-learning-decoded-how-neural-networks-are-chang…
## Towards AI. # Deep Learning Decoded: How Neural Networks Are Changing Everything. Deep Learning explained: How neural networks work, deep learning vs machine learning, architectures (CNNs, RNNs, Transformers), applications, and getting started with deep learning in 2025. ## What Is Deep Learning? **Deep Learning is a subset of Machine Learning that uses artificial neural networks with multiple layers (hence “deep”) to learn complex patterns from large amounts of data.**. * **Deep Learning:** Let the network automatically discover features through many layers of transformation. ## More from Gulshan Yadav and Towards AI. ### How to transform Claude from a chatbot into an AI that can code, browse, access your data, and automate your entire workflow. See all from Towards AI. ### You Just Need to Learn How to Use It. I Stopped Using ChatGPT for 30 Days. Vibe Coding is Over illustration of three ai generated landing pages with the words IT’S OVER written at the top in large text.
O
online.nyit.edu
research
https://online.nyit.edu/blog/deep-learning-and-neural-networks
[Skip to main content](https://online.nyit.edu/blog/deep-learning-and-neural-networks#main-content). * [Curriculum](https://online.nyit.edu/ms-data-science/curriculum). * [Careers](https://online.nyit.edu/ms-data-science/careers). * [Study at New York Tech](https://online.nyit.edu/ms-data-science/new-york). * [Apply Now](https://online.nyit.edu/blog/deep-learning-and-neural-networks#apply-now). [](https://online.nyit.edu/). * [Curriculum](https://online.nyit.edu/ms-data-science/curriculum). * [Careers](https://online.nyit.edu/ms-data-science/careers). * [Study at New York Tech](https://online.nyit.edu/ms-data-science/new-york). * [Apply Now](https://online.nyit.edu/blog/deep-learning-and-neural-networks#apply-now). [Home](https://online.nyit.edu/)[Online Degrees Blog at New York Tech](https://online.nyit.edu/blog)Deep Learning and Neural Networks: The Future of Machine Learning. . In contrast, deep learning programs use thousands of layers to train a model.2. An [Online Master’s in Data Science](https://online.nyit.edu/ms-data-science) from the New York Institute of Technology can equip you with the knowledge and skills you need to thrive in high-demand, data-driven careers. 2. Retrieved on May 9, 2025, from [ibm.com/think/topics/deep-learning](https://www.ibm.com/think/topics/deep-learning). 8. Retrieved on May 9, 2025, from [neurond.com/blog/10-applications-of-deep-learning-in-artificial-intelligence](https://www.neurond.com/blog/10-applications-of-deep-learning-in-artificial-intelligence). New York Institute of Technology has engaged [Everspring](https://online.nyit.edu/privacy-policy), a leading provider of education and technology services, to support select aspects of program delivery. [](https://online.nyit.edu/).
G
geeksforgeeks.org
article
https://www.geeksforgeeks.org/machine-learning/neural-network-advances/
This allows the network to learn more complex patterns as both connections and neurons can change during training. The key difference is that this approach allows network to learn from how neurons connect and interact with each other rather than just focusing on individual neuron behavior. Liquid Neural Networks are designed to continuously adapt to new information over time. These networks do not require retraining from scratch they get changed based on new data which is useful for real-time and dynamic applications. These networks learn slowly and can adjust themselves as new information comes in. : In fraud detection these networks can quickly learn how new ways fraud happens. Graph Neural Networks (GNNs) are designed to handle data that is organized like a network where data points (nodes) are connected to each other. Neural Processing Units (NPUs) are special chips made to speed up machine learning and AI tasks. + What is Machine Learning Pipeline? + Hierarchical Clustering in Machine Learning.
S
scispace.com
article
https://scispace.com/pdf/advancements-in-deep-learning-theory-and-application…
For more information visit www.intechopen.com Open access books available Countries delivered to Contributors from top 500 universities International authors and editors Our authors are among the most cited scientists Downloads We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists 12.2% 145,000 180M TOP 1% 154 5,900 1 Chapter Advancements in Deep Learning Theory and Applications: Perspective in 2020 and beyond Md Nazmus Saadat and Muhammad Shuaib Abstract The aim of this chapter is to introduce newcomers to deep learning, deep learning platforms, algorithms, applications, and open-source datasets. Advances and Applications in Deep Learning 10 4.1 TensorFlow The TensorFlow is new and open-source platform for differential programming; it was developed by Google team called Google brain and was first released in 2015 [24]. 7. Available open-source datasets Research in machine learning and deep learning is started since last many decades hence significant improvement it brings to the society in terms of various application-based on deep learning and machine learning.