Search for dissertations about: "Foteini Liwicki"
Found 5 swedish dissertations containing the words Foteini Liwicki.
-
1. Vector Representations of Idioms in Data-Driven Chatbots for Robust Assistance
Abstract : This thesis presents resources capable of enhancing solutions of some Natural Language Processing (NLP) tasks, demonstrates the learning of abstractions by deep models through cross-lingual transferability, and shows how deep learning models trained on idioms can enhance open-domain conversational systems. The challenges of open-domain conversational systems are many and include bland repetitive utterances, lack of utterance diversity, lack of training data for low-resource languages, shallow world-knowledge and non-empathetic responses, among others. READ MORE
-
2. Data driven crop disease modeling
Abstract : The concept of precision farming deals with the creation and use of data from machinery and sensors on and off the field to optimize resources and sustainably intensify food production to keep up with increasing demand. However, in the face of a growing amount of data being collected, smarter data processing and analysis techniques are needed and have prompted the evaluation and incorporation of artificial intelligence (AI) and machine learning (ML) techniques for multiple use cases right from seeding to harvesting. READ MORE
-
3. Event-Driven Architectures for Heterogeneous Neuromorphic Computing Systems
Abstract : Mixed-signal neuromorphic processors have brain-like organization and device physics optimized for emulation of spiking neural networks (SNNs), and offer an energy-efficient alternative for implementing artificial intelligence in applications where deep learning based on conventional digital computing is unfeasible or unsustainable. However, efficient use of such hardware requires appropriate configuration of its inhomogeneous, analog neurosynaptic circuits, with methods for sparse, spike-timing-based information encoding and processing. READ MORE
-
4. Using Inhomogeneous Neuronal–Synaptic Dynamics for Spatiotemporal Pattern Recognition in Neuromorphic Processors
Abstract : Mixed-signal neuromorphic processors emulate the electrochemical dynamics of neurons and synapses using conventional analog CMOS-transistor technology and have potential for ultra-low-power machine learning and inference. However, the energy-efficiency of such systems is dependent on sparse, time-based information encoding and processing, and they are, furthermore, subject to imprecision from “device mismatch” in the analog circuitry. READ MORE
-
5. Lithostratigraphy and alteration at the Rävliden North VMS deposit, Skellefte district, Sweden
Abstract : Technological and societal developments in the past century have greatly increased our society’s demand for metals, many which occur in polymetallic ores mined in the Skellefte district, northern Sweden. Near-surface deposits are becoming depleted and as such targeting of deep deposits is needed, which places special demand on effective management, processing and interpretation of geological data obtained from exploration drill holes. READ MORE