Sökning: "conventional reinforcement"

Visar resultat 1 - 5 av 56 uppsatser innehållade orden conventional reinforcement.

1. 1. Machine Learning-Based Instruction Scheduling for a DSP Architecture Compiler : Instruction Scheduling using Deep Reinforcement Learning and Graph Convolutional Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Lucas Alava Peña; [2023]
   Nyckelord :Instruction Scheduling; Deep reinforcement Learning; Compilers; Graph Convolutional Networks; Schemaläggning av instruktioner; Deep Reinforcement Learning; kompilatorer; grafkonvolutionella nätverk;

   Sammanfattning : Instruction Scheduling is a back-end compiler optimisation technique that can provide significant performance gains. It refers to ordering instructions in a particular order to reduce latency for processors with instruction-level parallelism. LÄS MER

3. 2. Battery Storage as Grid Reinforcement for Peak Power Demands

   Master-uppsats, Linköpings universitet/Energisystem

   Författare :Jesper Hilleberg; [2023]
   Nyckelord :Battery Storage; Battery Energy Storage System; Grid Reinforcement; Flexibility; Lithium-ion battery; li-ion battery; Large Scale Grid Storage; BESS; Energy Storage; Peak Power Demand; Batterilagring; Batterilagringsystem; Nätförstärkning; Nätförstärkningsåtgärd; toppeffektlaster; Flexibilitet; Flexibilitetslösning; litiumjonbatteri; li-ion batteri; BESS; energilagring;

   Sammanfattning : An increased amount of intermittent electricity production, more electric vehicles (EV), and an overall electrification of society may all cause a higher variability between the balance of supply and demand on the electric grid. Battery storage has been identified as a solution to the emerging problem asit can be charged during hours of low power demand and then discharged to help meet the power demand during peak loads. LÄS MER

4. 3. Gymcels: incels samtida utlöpare på sociala medier

   Kandidat-uppsats, Lunds universitet/Sociologi

   Författare :Gabriel Jaeger; [2023]
   Nyckelord :Internet; Extremism; Masculinity; Incels; Technology; Gymcels; Subculture; Manosphere; Tiktok; Social media; Social Sciences;

   Sammanfattning : In this paper the studied subject is the recent offshoot of incels: gymcels and associated terms such as sigma among others. This study investigates what this subsect implies and does so by defining aspects of conventional incel culture and juxtaposes these with gymcel cultures own differing ones. LÄS MER

5. 4. Using Reinforcement Learning to Correct Soft Errors of Deep Neural Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Yuhang Li; [2023]
   Nyckelord :DNN; Soft errors; Redundancy; DRL; DQN; Transfer learning; Training time; DNN; Mjuka fel; Redundans; DRL; DQN; Överföringsinlärning; Utbildningstid;

   Sammanfattning : Deep Neural Networks (DNNs) are becoming increasingly important in various aspects of human life, particularly in safety-critical areas such as autonomous driving and aerospace systems. However, soft errors including bit-flips can significantly impact the performance of these systems, leading to serious consequences. LÄS MER

7. 5. Improving Co-existence of URLLC and Distributed AI using RL

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Wei Shi; [2023]
   Nyckelord :5G; URLLC; RL; HRL; Optimization; 5G; URLLC; RL; HRL; Optimering;

   Sammanfattning : In 5G, Ultra-reliable and low-Latency communications (URLLC) service is envisioned to enable use cases with strict reliability and latency requirements on wireless communication. For the upcoming 6G network, machine learning (ML) also stands an important role that introduces intelligence and further enhances the system performance. LÄS MER