Jezik: | Slovenski jezik |
---|---|
Leto izida: | 2024 |
Tipologija: | 2.11 - Diplomsko delo |
Organizacija: | UL FMF - Fakulteta za matematiko in fiziko |
Založnik: | [T. Dolenc] |
UDK: | 004.8 |
COBISS: |
206082819
![]() |
Št. ogledov: | 34 |
Št. prenosov: | 11 |
Ocena: | 0 (0 glasov) |
Metapodatki: |
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Sekundarni jezik: | Angleški jezik |
---|---|
Sekundarni naslov: | Reccurent neural networks and their applications |
Sekundarni povzetek: | The thesis explores feedforward neural networks and recurrent neural networks (RNNs). It presents the fundamental characteristics and learning algorithms for both types of networks and introduces an additional method for representing the loss function gradient in RNNs. The work also includes a custom implementation of a feedforward neural network and the application of RNNs to the problem of forecasting electricity consumption. The results indicate that RNNs are suitable for short-term time series forecasting, although they face challenges such as exploding and vanishing gradients. |
Sekundarne ključne besede: | neural networks;feedforward neural networks;recurrent neural networks;time series forecasting;loss function gradient;chain rule;backpropagation; |
Vrsta dela (COBISS): | Delo diplomskega seminarja/zaključno seminarsko delo/naloga |
Študijski program: | 0 |
Komentar na gradivo: | Univ. v Ljubljani, Fak. za matematiko in fiziko, Oddelek za matematiko, Finančna matematika - 1. stopnja |
Strani: | 27 str. |
ID: | 24870429 |