Reset
Showing 20 of 62 academic articles

The Role and Application of Matrices in Artificial Intelligence: Foundations, Methods, and Advancements

Raviraju Balappa D, Gautam Kumar Rajput • Shodh Sari (2025)

Matrices are foundational to artificial intelligence (AI), serving as critical tools for data representation, manipulation, and transformation across various applications. From machine learning algorithms to neural network architectures, ma...

DOAJ Open Access (DOAJ) DOI: https://doi.org/10.59231/SARI7840

Natural Language Processing

Santanu Pattanayak • Apress eBooks (2022)

In the modern age of information and analytics, natural language processing (NLP) is one of the most important technologies out there. Making sense of complex structures in language and deriving insights and actions from it are crucial from...

OPENALEX DOI: https://doi.org/10.1007/978-1-4842-8931-0_4

LSTM neural networks for language modeling

Martin Sundermeyer, Ralf Schlüter, Hermann Ney • Interspeech (USB) (2012)

Neural networks have become increasingly popular for the task of language modeling.Whereas feed-forward networks only exploit a fixed context length to predict the next word of a sequence, conceptually, standard recurrent neural networks ca...

OPENALEX Open Access DOI: https://doi.org/10.21437/interspeech.2012-65

Recurrent Neural Networks for Prediction

Danilo P. Mandic, Jonathon A. Chambers • Wiley eBooks (2001)

New technologies in engineering, physics and biomedicine are demanding increasingly complex methods of digital signal processing. By presenting the latest research work the authors demonstrate how real-time recurrent neural networks (RNNs) ...

OPENALEX DOI: https://doi.org/10.1002/047084535x

Hyperbolic Neural Networks

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann • arXiv (Cornell University) (2018)

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geomet...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1805.09112

Optimization using neural networks

Gene A. Tagliarini, John Fury Christ, Edward W. Page • IEEE Transactions on Computers (1991)

The design of feedback (or recurrent) neural networks to produce good solutions to complex optimization problems is discussed. The theoretical basis for applying neural networks to optimization problems is reviewed, and a design rule that s...

OPENALEX DOI: https://doi.org/10.1109/12.106220

Bidirectional recurrent neural networks

Mike Schuster, Kuldip K. Paliwal • IEEE Transactions on Signal Processing (1997)

In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future f...

OPENALEX DOI: https://doi.org/10.1109/78.650093

Self-Normalizing Neural Networks

Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter • arXiv (Cornell University) (2017)

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNN...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1706.02515

Recurrent Neural Network Regularization

Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals • arXiv (Cornell University) (2014)

We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In ...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1409.2329

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El‐Yaniv et al. • arXiv (Cornell University) (2016)

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing ...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1609.07061

Applications of Neural Networks in Electromagnetics

Christos Christodoulou, Michael Georgiopoulos • CERN Document Server (European Organization for Nuclear Research) (2001)

From the Book: Since the early 1990s, a plethora of electromagnetic problems have been tackled using neural networks, some more successfully than others. Because neural networks and electromagnetics are two different scientific fields, not...

OPENALEX

Recurrent Neural Networks

• CRC Press eBooks (1999)

From the Publisher: With applications ranging from motion detection to financial forecasting, recurrent neural networks (RNNs) have emerged as an interesting and important part of neural network research. Recurrent Neural Networks: Design ...

OPENALEX DOI: https://doi.org/10.1201/9781420049176

Deep hybrid neural net (DHN-Net) for minute-level day-ahead solar and wind power forecast in a decarbonized power system

Olusola Bamisile, Dongsheng Cai, Humphrey Adun, Chukwuebuka Ejiyi et al. • Energy Reports (2023)

The need to reduce global carbon emissions has led to a significant increase in clean energy globally. While renewable energy penetration into energy grids and power systems is increasing in many countries, the intermittency and stochastic ...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.egyr.2023.05.229

A recurrent neural network framework for flexible and adaptive decision making based on sequence learning.

Zhewei Zhang, Huzi Cheng, Tianming Yang • PLoS Computational Biology (2020)

The brain makes flexible and adaptive responses in a complicated and ever-changing environment for an organism's survival. To achieve this, the brain needs to understand the contingencies between its sensory inputs, actions, and rewards. Th...

DOAJ Open Access (DOAJ) DOI: 10.1371/journal.pcbi.1008342

Comparative Study of CNN and RNN for Natural Language Processing

Wenpeng Yin, Katharina Kann, Mo Yu, Hinrich Schütze • arXiv (Cornell University) (2017)

Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN), the two main types of DNN architectures, are widely explored to handle var...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1702.01923