Sökning: "randomly generated networks"
Visar resultat 1 - 5 av 15 uppsatser innehållade orden randomly generated networks.
1. 3D Modeling of Factory Scenarios for 5G Evaluations
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : 5G is a key enabler for a variety of use cases in smart manufacturing which requires communications with high reliability and low latency. In a dynamic industrial environment, objects such as machines, production lines, storage shelves, robotic arms, and automatically guided vehicles may cause fading and have a large impact on radio propagation. LÄS MER
2. Practical Analysis of the Giskard Consensus Protoco
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Consensus protocols are the core of modern blockchain systems, such as the Bitcoin, Ethereum, and Algorand networks. Thanks to these protocols, participants in a blockchain network can reach consensus on which blocks to add to a blockchain, to have a consistent chain of blocks in the whole network. LÄS MER
3. Synthesis of Neural Networks using SAT Solvers
Kandidat-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Artificial neural networks (ANN) have found extensive use in solving real-world problems in recent years, where their exceptional information processing is the main advantage. Facing increasingly complex problems, there is a need to improve their information processing. LÄS MER
4. Imputing connections of random gene networks from time series data using ANNs
Master-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisationSammanfattning : This thesis presents the architecture of a convolutional neural network which is trained to impute the connections of randomly generated gene regulatory networks under varying amounts of regularisation. The generated gene networks are simulated from 10 different starting conditions for each set of connections in order to obtain multiple time series. LÄS MER
5. Transfer Learning in Deep Structured Semantic Models for Information Retrieval
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Recent approaches to IR include neural networks that generate query and document vector representations. The representations are used as the basis for document retrieval and are able to encode semantic features if trained on large datasets, an ability that sets them apart from classical IR approaches such as TF-IDF. LÄS MER