Essays about: "Gradient Decent"
Showing result 1 - 5 of 6 essays containing the words Gradient Decent.
-
1. Optimizing First-Order Method Parameters via Differentiation of the Performance Estimation Problem
University essay from Lunds universitet/Institutionen för reglerteknikAbstract : This thesis treats the problem of finding optimal parameters for first-order optimization methods. In part, we use the Performance Estimation Problem (PEP), a framework for convergence analysis of first-order optimization methods. READ MORE
-
2. Building and Training a Fully Connected Deep Neural Network From Scratch
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Artificial Neural Networks make up the core of mostMachine Learning algorithms. In the past decade Machine learninghave successfully taken on fields such as image recognition,Data analytics and medical technologies. READ MORE
-
3. Predicting Risk of Delays in Postal Deliveries with Neural Networks and Gradient Boosting Machines
University essay from Linköpings universitet/Institutionen för datavetenskapAbstract : This thesis conducts a study on a data set from the Swedish and Danish postal service Postnord, comparing an artificial neural network (ANN) and a gradient boosting machine (GBM) for predicting delays in package deliveries. The models are evaluated based on F1-score for the important class which represents the data points that are delayed and needed to be identified. READ MORE
-
4. Interpretation of Swedish Sign Language using Convolutional Neural Networks and Transfer Learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : The automatic interpretation of signs of a sign language involves image recognition. An appropriate approach for this task is to use Deep Learning, and in particular, Convolutional Neural Networks. This method typically needs large amounts of data to be able to perform well. READ MORE
-
5. Video Flow Classification : A Runtime Performance Study
University essay from Karlstads universitet/Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)Abstract : Due to it being increasingly common that users' data is encrypted, the Internet service providers today find it difficult to adapt their service for the users' needs. Previously popular methods of classifying users data does not work as well today and new alternatives is therefore desired to give the users an optimal experience. READ MORE