Sökning: "Automatic Differentiation"

Visar resultat 1 - 5 av 17 uppsatser innehållade orden Automatic Differentiation.

1. 1. Learning by Digging : A Differentiable Prediction Model for an Autonomous Wheel Loader

   Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

   Författare :Arvid Fälldin; [2022]
   Nyckelord :Wheel loader; Deep learning; Autonomous; Multibody and soil dynamics;

   Sammanfattning : Wheel loaders are heavy duty machines that are ubiquitous on construction sites and in mines all over the world. Fully autonomous wheel loaders remains an open problem but the industry is hoping that increasing their level of autonomy will help to reduce costs and energy consumption while also increasing workplace safety. LÄS MER

3. 2. Physics-informed Neural Networks for Biopharma Applications

   Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

   Författare :Linnéa Cedergren; [2021]
   Nyckelord :PINN; PINNs; physics-informed neural networks; neural networks; machine learning; sartorius; CSTR;

   Sammanfattning : Physics-Informed Neural Networks (PINNs) are hybrid models that incorporate differential equations into the training of neural networks, with the aim of bringing the best of both worlds. This project used a mathematical model describing a Continuous Stirred-Tank Reactor (CSTR), to test two possible applications of PINNs. LÄS MER

4. 3. Differential Deep Learning for Pricing Exotic Financial Derivatives

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

   Författare :Erik Alexander Aslaksen Jonasson; [2021]
   Nyckelord :Deep Learning; Exotic Derivatives; Differential Machine Learning;

   Sammanfattning : Calculating the value of a financial derivative is a central problem in quantitative finance. For many exotic derivatives there are no closed-form solutions for present values, instead, computationally expensive Monte Carlo methods are used for valuation. LÄS MER

5. 4. Deep learning exotic derivatives

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

   Författare :Gunnlaugur Geirsson; [2021]
   Nyckelord :deep learning; neural networks; derivative pricing; automatic differentiation; Monte Carlo; transfer learning; structured products; risk sensitivities; valuation; autocalls;

   Sammanfattning : Monte Carlo methods in derivative pricing are computationally expensive, in particular for evaluating models partial derivatives with regard to inputs. This research proposes the use of deep learning to approximate such valuation models for highly exotic derivatives, using automatic differentiation to evaluate input sensitivities. LÄS MER

7. 5. Tacit collusion with deep multi-agent reinforcement learning

   D-uppsats, Handelshögskolan i Stockholm/Institutionen för nationalekonomi

   Författare :Filip Mellgren; [2020]
   Nyckelord :deep multi-agent reinforcement learning; tacit collusion; pricing algorithms;

   Sammanfattning : Automatic pricing now attracts the attention of competition authorities following recent machine learning developments. In particular, previous research shows that the Q-learning algorithm can reach collusive outcomes despite receiving only minimal human intervention. LÄS MER