Search for dissertations about: "new neural networks"
Showing result 1 - 5 of 154 swedish dissertations containing the words new neural networks.
-
1. Characterizing Piecewise Linear Neural Networks
Abstract : Neural networks utilizing piecewise linear transformations between layers have in many regards become the default network type to use across a wide range of applications. Their superior training dynamics and generalization performance irrespective of the nature of the problem has resulted in these networks achieving state of the art results on a diverse set of tasks. READ MORE
-
2. Word Vector Representations using Shallow Neural Networks
Abstract : This work highlights some important factors for consideration when developing word vector representations and data-driven conversational systems. The neural network methods for creating word embeddings have gained more prominence than their older, count-based counterparts. READ MORE
-
3. Infrared Neural Modulation: Photothermal Effects on Cortex Neurons Using Infrared Laser Heating
Abstract : It would be of great value to have a precise and non-damaging neuromodulation technique in the field of basic neuroscience research and for clinical treatment of neurological diseases. Infrared neural modulation (INM) is a new modulation modality developed in the last decade, which uses pulsed or continues infrared (IR) light with a wavelength of 1200 to 2200 nm to directly alter neural signals. READ MORE
-
4. Machine Learning Methods for Image Analysis in Medical Applications, from Alzheimer's Disease, Brain Tumors, to Assisted Living
Abstract : Healthcare has progressed greatly nowadays owing to technological advances, where machine learning plays an important role in processing and analyzing a large amount of medical data. This thesis investigates four healthcare-related issues (Alzheimer's disease detection, glioma classification, human fall detection, and obstacle avoidance in prosthetic vision), where the underlying methodologies are associated with machine learning and computer vision. READ MORE
-
5. On Improving Validity of Deep Neural Networks in Safety Critical Applications
Abstract : Context: Deep learning has proven to be a valuable component in object detection and classification, as the technique has shown an increased performance throughput compared to traditional software algorithms. Deep learning refers to the process, in which an optimisation process learns an algorithm through a set of labeled data, where the researcher defines an architecture rather than the algorithm itself. READ MORE