Indiana University-Purdue University Indianapolis (IUPUI) / Mutual learning algorithm is a machine learning algorithm where multiple machine learning algorithms learns from different sources and then share their knowledge among themselves so that all the agents can improve their classification and prediction accuracies simultaneously. Mutual learning algorithm can be an efficient mechanism for improving the machine learning and neural network efficiency in a multi-agent system. Usually, in knowledge distillation algorithms, a big network plays the role of a static teacher and passes the data to smaller networks, known as student networks, to improve the efficiency of the latter. In this thesis, it is showed that two small networks can dynamically and interchangeably play the changing roles of teacher and student to share their knowledge and hence, the efficiency of both the networks improve simultaneously. This type of dynamic learning mechanism can be very useful in mobile environment where there is resource constraint for training with big dataset. Data exchange in multi agent, teacher-student network system can lead to efficient learning. The concept and the proposed mutual learning algorithm are demonstrated using convolutional neural networks (CNNs) and Support Vector Machine (SVM) to recognize the pattern recognition problem using MNIST hand-writing dataset. The concept of machine learning is applied in the field of natural language processing (NLP) too. Machines with basic understanding of human language are getting increasingly popular in day-to-day life. Therefore, NLP-enabled machines with memory efficient training can potentially become an indispensable part of our life in near future. A classic problem in the field of NLP is news classification problem where news articles from newspapers are classified by news categories by machine learning algorithms. In this thesis, we show news classification implemented using Naïve Bayes and support vector machine (SVM) algorithm. Then we show two small networks can dynamically play the changing roles of teacher and student to share their knowledge on news classification and hence, the efficiency of both the networks improves simultaneously. The mutual learning algorithm is applied between homogenous algorithms first, i.e., between two Naive Bayes algorithms and two SVM algorithms. Then the mutual learning is demonstrated between heterogenous agents, i.e., between one Naïve Bayes and one SVM agent and the relative efficiency increase between the agents is discussed before and after mutual learning. / 2025-04-04

Målet med studien var att undersöka skalning av tidsåtgång och minnesanvändning utifrån tre stycken algoritmer som procedurellt genererar banor. De algoritmerna som används är Binary Space Partitioning (BSP), Shortest Path (SP) och Delaunay Triangulation (DT). Skalningen utvärderas genom att se hur tidsåtgången och minnesanvändningen påverkas då algoritmerna ska hantera större banor. Värdena för tid och minne sammanställdes sedan för att avgöra hur de skalade, till vilken grad de var användbara och vilken av algoritmerna som presterade bäst. Utvärderingen visade att BSP presterade bäst i båda kategorierna med relativt jämna värden. SP hade generellt väldigt spretiga tidsvärden. DT var långsammast av de tre algoritmerna i avseende på tid men presterade bättre än SP när det kom till minnesanvändning. Skalning av minne visade sig vara ett mindre problem än förväntat vilket inte är något problem för plattformar som inte är begränsade inbäddade system, exempelvis mikroprocessorer. Framtida studier hade kunnat testa andra algoritmer. / <p>Det finns övrigt digitalt material (t.ex. film-, bild- eller ljudfiler) eller modeller/artefakter tillhörande examensarbetet som ska skickas till arkivet.</p><p>There are other digital material (eg film, image or audio files) or models/artifacts that belongs to the thesis and need to be archived.</p>

In this study, the parameters of population, gross domestic product (GDP), heat price, U-value, and temperature have been used to predict heat consumption for Sweden till 2050. It should be noted that the heat consumption has been considered for multi-family houses. Most multi-family houses (MFH) get their primary heat from district heating (DH). A literature analysis of various models and variables has been conducted to enhance comprehension of forecasting and its process. The majority of earlier research has focused on electricity or energy rather than heat. The aim of this study is to create a model (linear and non-linear) from 1993 to 2019 with a minimum error as possible, and then use the genetic algorithm (GA) and neural network (NN) to predict Sweden's heat consumption till 2050

No / A new approach in achieving beam steering in array antenna is introduced using the genetic algorithm optimization. The binary switching technique uses simple binary ON/OFF diodes placed in the feeding network of the array element to achieve beam steering. Constantly feeding the driven element and continuous binary variation of the ON/OFF state of each parasitic array elements which determines its conducting ability defines a beam steering angle. Each beam steered angle is distinguished by series of binary combination determined by the genetic algorithm. A uniform circular array antenna consisting of 13 elements is used to implement this technique. The simulation and result analysis of the binary switched array is presented with several beam steering angles scanned.

Reinforcement learning (RL) has received attention in recent years from agent-based researchers because it can be applied to problems where autonomous agents learn to select proper actions for achieving their goals based on interactions with their environment. Each time an agent performs an action, the environment¡Šs response, as indicated by its new state, is used by the agent to reward or penalize its action. The agent¡Šs goal is to maximize the total amount of reward it receives over the long run. Although there have been several successful examples demonstrating the usefulness of RL, its application to manufacturing systems has not been fully explored. The objective of this research is to develop a set of guidelines for applying the Q-learning algorithm to enable an individual agent to develop a decision making policy for use in agent-based production scheduling applications such as dispatching rule selection and job routing. For the dispatching rule selection problem, a single machine agent employs the Q-learning algorithm to develop a decision-making policy on selecting the appropriate dispatching rule from among three given dispatching rules. In the job routing problem, a simulated job shop system is used for examining the implementation of the Q-learning algorithm for use by job agents when making routing decisions in such an environment. Two factorial experiment designs for studying the settings used to apply Q-learning to the single machine dispatching rule selection problem and the job routing problem are carried out. This study not only investigates the main effects of this Q-learning application but also provides recommendations for factor settings and useful guidelines for future applications of Q-learning to agent-based production scheduling.

No description available.

No description available.

No description available.

No description available.

No description available.