Advanced search
Showing result 1 - 5 of 47 essays matching the above criteria.
-
1. Flood Prevention Governance of Paris : The Issue of Institutional Fragmention in the Attempt of Reconnecting to the Biosphere
University essay from Linköpings universitet/Institutionen för temaAbstract : Paris has been recurrently affected by floods in the recent years. Such events of heavy precipitations are expected to grow in intensity while being concentrated on shorter periods of time. Subsequently, the risk of floods will increase. The municipality must act accordingly and achieve resilience. READ MORE
-
2. Vulnerabilities in Swedish Industrial Control Systems : An examination and classification of remotely discoverable ICS devices in Sweden, and an assessment of their vulnerability to cyber attacks
University essay from KTH/DatavetenskapAbstract : Over the last couple of years, more and more industrial control systems (ICS) have been designed to be connected to the internet to allow for remote control and monitoring of industrial processes. This have opened a possibility for hackers to exploit weaknesses in such systems remotely through the internet. READ MORE
-
3. Post-processing of optical character recognition for Swedish addresses
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Optical character recognition (Optical Character Recognition (OCR)) has many applications, such as digitizing historical documents, automating processes, and helping visually impaired people read. However, extracting text from images into a digital format is not an easy problem to solve, and the outputs from the OCR frameworks often include errors. READ MORE
-
4. Use of Stochastic Switching in the Training of Binarized Neural Networks
University essay from Lunds universitet/Institutionen för elektro- och informationsteknikAbstract : Most prior research into the field of Binarized Neural Networks (BNNs) has been motivated by a desire to optimize Deep Learning computations on traditional hardware. These methods rely on bit-wise operations to drastically decrease computation time, however to address the resulting loss in accuracy it is common practice to reintroduce continuous parameters and train using batch normalization. READ MORE
-
5. Investigating Few-Shot Transfer Learning for Address Parsing : Fine-Tuning Multilingual Pre-Trained Language Models for Low-Resource Address Segmentation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Address parsing is the process of splitting an address string into its different address components, such as street name, street number, et cetera. Address parsing has been quite extensively researched and there exist some state-ofthe-art address parsing solutions, mostly unilingual. READ MORE