Graph Neural Networks
Graph Neural Networks (GNNs) are a versatile form of neural networks that encompass various network architectures like NNs, CNNs, and RNNs, as well as unsupervised learning models such as RBM and DBNs. They find applications in diverse fields such as object detection, machine translation, and drug d
2 views • 48 slides
Recent Advances in RNN and CNN Models: CS886 Lecture Highlights
Explore the fundamentals of recurrent neural networks (RNNs) and convolutional neural networks (CNNs) in the context of downstream applications. Delve into LSTM, GRU, and RNN variants, alongside CNN architectures like ConvNext, ResNet, and more. Understand the mathematical formulations of RNNs and c
1 views • 76 slides
Exploring a Cutting-Edge Convolutional Neural Network for Speech Emotion Recognition
Human speech is a rich source of emotional indicators, making Speech Emotion Recognition (SER) vital for intelligent systems to understand emotions. SER involves extracting emotional states from speech and categorizing them. This process includes feature extraction and classification, utilizing tech
1 views • 15 slides
Understanding Convolutional Neural Networks: Architectural Characterizations for Accuracy Inference
This presentation by Duc Hoang from Rhodes College explores inferring the accuracy of Convolutional Neural Networks (CNNs) based on their architectural characterizations. The talk covers the MINERvA experiment, deep learning concepts including CNNs, and the significance of predicting CNN accuracy be
0 views • 21 slides
CNN-based Multi-task Learning for Crowd Counting: A Novel Approach
This paper presents a novel end-to-end cascaded network of Convolutional Neural Networks (CNNs) for crowd counting, incorporating high-level prior and density estimation. The proposed model addresses the challenge of non-uniform large variations in scale and appearance of objects in crowd analysis.
1 views • 17 slides
Utilizing Deep Learning for Privacy Verification in Mobile and Web Apps
Mobile and web apps are collecting personal information, posing privacy risks. Compliance verification is challenging, but deep learning can help maintain an ontology of information types, reducing ambiguity and improving analysis accuracy, as demonstrated by Convolutional Neural Networks (CNNs) in
0 views • 39 slides
Convolutional Neural Networks for Sentence Classification: A Deep Learning Approach
Deep learning models, originally designed for computer vision, have shown remarkable success in various Natural Language Processing (NLP) tasks. This paper presents a simple Convolutional Neural Network (CNN) architecture for sentence classification, utilizing word vectors from an unsupervised neura
0 views • 15 slides
Exploring RNNs and CNNs for Sequence Modelling: A Dive into Recent Trends and TCN Models
Today's presentation will delve into the comparison between RNNs and CNNs for various tasks, discuss a state-of-the-art approach for Sequence Modelling, and explore augmented RNN models. The discussion will include empirical evaluations, baseline model choices for tasks like text classification and
0 views • 20 slides
Event Classification in Sand with Deep Learning: DUNE-Italia Collaboration
Alessandro Ruggeri presents the collaboration between DUNE-Italia and Nu@FNAL Bologna group on event classification in sand using deep learning. The project involves applying machine learning to digitized STT data for event classification, with a focus on CNNs and processing workflows to extract pri
0 views • 11 slides
Emerging Variable Precision Formats in Compiler Flow
Many applications rely on floating point numbers, but deciding on the right precision is crucial to avoid performance and energy waste. This work explores the impact of precision choices, including overkill and insufficient precision, on applications such as CNNs and GPU algorithms. It introduces a
0 views • 25 slides