Advanced search
Showing result 1 - 5 of 48 essays matching the above criteria.
-
1. Methods for Developing TinyConvolutional Neural Networksfor Deployment on EmbeddedSystems
University essay from Uppsala universitet/Institutionen för informationsteknologiAbstract : With the recent development in the Deep Learning area, computationally heavy tasks like object detection in images have become easier to compute and take less time to execute with powerful GPUs. Also, when employing sufficiently larger models, these daily tasks are predicted with greater accuracy. READ MORE
-
2. Low-power Implementation of Neural Network Extension for RISC-V CPU
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep Learning and Neural Networks have been studied and developed for many years as of today, but there is still a great need of research on this field, because the industry needs are rapidly changing. The new challenge in this field is called edge inference and it is the deployment of Deep Learning on small, simple and cheap devices, such as low-power microcontrollers. READ MORE
-
3. Investigation of 8-bit Floating-Point Formats for Machine Learning
University essay from Linköpings universitet/DatorteknikAbstract : Applying machine learning to various applications has gained significant momentum in recent years. However, the increasing complexity of networks introduces challenges such as a larger memory footprint and decreased throughput. This thesis aims to address these challenges by exploring the use of 8-bit floating-point numbers for machine learning. READ MORE
-
4. Reverse Engineering of Deep Learning Models by Side-Channel Analysis
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Side-Channel Analysis (SCA) aims to extract secrets from cryptographic systems by exploiting the physical leakage acquired from implementations of cryptographic algorithms. With the development of Deep Learning (DL), a new type of SCA called Deep Learning Side-Channel Analysis (DLSCA) utilizes the advantages of DL techniques in data features processing to break cryptographic systems more efficiently. READ MORE
-
5. Mixed Precision Quantization for Computer Vision Tasks in Autonomous Driving
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Quantization of Neural Networks is popular technique for adopting computation intensive Deep Learning applications to edge devices. In this work, low bit mixed precision quantization of FPN-Resnet18 model trained for the task of semantic segmentation is explored using Cityscapes and Arriver datasets. READ MORE