Search
5 articles for “SGD”
-
Gradient Boosted Regression Tree Approach to Predicting Toxic Interactions on X and YouTube
Abstract: In the digital age, social media platforms play a vital role in facilitating user engagement, encompassing both positive interactions and avenues for negative, often harmful behaviors. Recognizing and addressing toxic exchanges is paramount to nurturing healthy online communities and preserving users’ well-being. This study introduces a novel method for identifying toxic interactions by utilizing Gradient Boosting Regression Trees (GBRT) algorithm, a machine learning approach renowned for its exceptional accuracy and …
Published in Trends in Opto-electro & Optical Communication · Vol. 15, Issue 3, 2025 · pp. 7–14 Read article
-
Fake News Detection Using N-Gram Analysis and Machine Learning Algorithms
Abstract: Fake news is untrue information presented as news. Fake news easily spread than real news amongst social networking sites. Detection of fake news is an important emerging research area which is gaining popularity. The main challenge in fake news detection is limited availability of resources (datasets). This project work detects fake news using n-gram analysis and machine learning algorithms. Evaluation and comparison between two feature extraction technique namely Term Frequency …
Published in Journal of Mobile Computing, Communications & Mobile Networks · Vol. 8, Issue 1, 2021 · pp. 33–43 Read article
-
Develop Institutional Chatbot Using Deep Neural Networks and NLTK
Abstract: Chatbots are intelligent software that can communicate and perform actions like those of a customer service representative. Chatbots are widely used for customer interaction and marketing on social networking and e-commerce sites. AI-based chatbots have the core ability to learn from any question based on initial training on a predefined dataset. A web-based platform provides a broad intelligent foundation for simulating human problem solving. The technology used here is based …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 10, Issue 3, 2023 · pp. 1–7 Read article
-
Accelerating Unsupervised Feature Learning: Parallelized Training of Denoising Autoencoders
Abstract: Unsupervised representation learning has become a cornerstone of contemporary machine learning, enabling algorithms to extract informative features from un-labelled, high-dimensional data. This work investigates the efficacy of stacked denoising autoencoders (SDAEs) trained via parallelized stochastic gradient descent (SGD) as a scalable approach to feature extraction. By strategically leveraging multi-threaded computation, our study systematically examines the trade-offs between increased parallelism, training efficiency, and the preservation of model accuracy. Experiments on the …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 3, 2025 · pp. 56–64 Read article
-
Handwritten Sanskrit Word Recognition: A Deep Learning Approach Using AlexNet
Abstract: Handwritten Sanskrit word recognition poses significant challenges due to the intricate structure of the script and the considerable variations in handwriting across individuals. To address these challenges, this research introduces a novel methodology employing transfer learning with the AlexNet convolutional neural network. The study utilized two distinct datasets: a specifically curated Sanskrit word image dataset containing 2616 samples, alongside a broader Devanagari character dataset used for validation purposes. The established …
Published in Current Trends in Signal Processing · Vol. 15, Issue 2, 2025 · pp. 33–43 Read article