E-raamat: Deep Learning Theory and Applications: 5th International Conference, DeLTA 2024, Dijon, France, July 10-11, 2024, Proceedings, Part II

Geometrical Realization for Time Series Forecasting.- Brains over Brawn:
Small AI Labs in the Age of Datacenter-Scale Compute.- Time Series Prediction
for Anomalies Detection in Concentrating Solar Power Plants Using Long
Short-Term Memory N Networks.- Bayes Classification Using an Approximation to
the Joint Probability Distribution of the Attributes.- Pollutant Source
Localization Based on Siamese Neural Network Similarity Measure.- Automatic
Emotion Analysis in Movies: Matteo Garrones Dogman as a Case Study.-
Empowering Cybersecurity: CyberShield AI Advanced Integration of Machine
Learning and Deep Learning for Dynamic Ransomware Detection.- Empirical
Performance of Deep Learning Models with Class Imbalance for Crop Disease
Classification.- Automating the Conducting of Surveys Using Large Language
Models.- Computer Vision Based Monitoring System for Flotation in Mining
Industry 4.0.- Self-Supervised Learning for Robust Surface Defect Detection.-
Efficient Deep Neural Network Verification with QAP-Based zkSNARK.- Version 8
of YOLO for Wildfire Detection.- Investigating a Semantic Similarity Loss
Function for the Parallel Training of Abstractive and Extractive Scientific
Document Summarizers.- Deep Learning-Based Preprocessing Tools for Turkish
Natural Language Processing.- Skin Cancer Classification: A Comparison of
CNN-Backbones for Feature-Extraction.- Multilingual Detection of
Cyberbullying on Social Networks Using a Fine-Tuned GPT-3.5 Model.- Detecting
Big-5 Personality Dimensions from Text Based on Large Language Models.-
ME-ODAL: Mixture-of-Experts Ensemble of CNN Models for 3D Object Detection
from Automotive LiDAR Point Clouds.- BitNet b1.58 Reloaded: State-of-the-Art
Performance Also on Smaller Networks.- Deep Learning for Cattle Face
Identification.- OBBabyFace: Oriented Bounding Box for Infant Face
Detection.- EEG-Based Patient Independent Epileptic Seizure Detection Using
GCN-BRF.- Predicting Components of a Target Value Versus Predicting the
Target Value Directly.