Top Research Papers on Machine Learning Projects

The outcomes of the current research illustrate the potential of ML modeling to be adopted for assigning productivity rates, making it a powerful tool for decision making.

It is shown that projective ML possesses the subject reduction property, which means that well-typed programs can be reduced safely and is built on by adding the ML Let typing rule to the simply typed projective calculus.

This dissertation examines the machine learning issues raised by the domain of anomaly detection for computer security by focusing here on learning models of normalcy at the user behavioral level.

This project created two models which are trained to detect neurons and axons using a modified version of the U-Net which uses a VGG pre-trained network as its encoder, and analyzed the directionality of the axons depending on the orientation of the grid formed by the nanostructure.

; ;

The scope of the program was widened while the focus on extensional viscosity measurements was retained, and attempts were made to have the same measurements repeated using different techniques and instruments.

A probabilistic method of finding meaningful phrases in the Twenty-Newsgroups text corpus by indexing terms which have length more than one is explored.

This thesis primarily investigates the potential of the Pairwise Geometric Histogram (PGH) representation as the basis of a machine learning edge and view-based 3D object recognition computer vision system, exploring methods for representing scaled 3D objects’ continuous appearances around their view-spheres.

This paper comprehensively examines the effects of Artificial Intelligence (AI), specifically machine learning on IT project management in the context of technologically advanced surroundings through a thorough literature review and detailed analysis.

A resource allocation method that uses machine learning for effective project scheduling that can be used to solve resource allocation problems of software project management.

The objective of this research is to use several algorithms of machine learning to estimate the effort of software project development and the best machine learning model is chosen to compare with the COCOMO.

It is concluded that the best compromise was a model using SSD detection and MOSSE tracking : the authors managed to achieve 31 fps and 63% of accuracy.

It is shown that it is impossible for the regret to be O(T 1− ), where T is the number of iterations, if the dependency of the regret on the other parameters is polynomial and if NP 6⊆ BPP, which is a big open problem that is believed to be true.

Even if a technical project is not research, and never has to be explained to outsiders, writing reports for internal use is a way to promote deep and careful thinking.

An overview of the requirements engineering challenges in the development of machine learning systems that have been reported in the research literature, along with their proposed solutions, and the approach to overcoming them in the form of a case study is presented.

Training neural audio classifiers with few data used prototypical networks and transfer learning to train the neural network and predicted the future trending on the smart devices.

It is found that the random projection approach predictively underperforms PCA, but its computational advantages may make it attractive for certain applications.

In this project, seven feature selection algorithms are applied to reduce the dimensionality of a molecular representation dataset with a huge number of features, and the prediction accuracy is compared.

This case study simulation demonstrates that the Melbourne Metro project has about 42% of the benefits felt in terms of public transport user gains, followed by road user gains linked to decongestion (21.5%), and the assets’ residual value, as well as externalities (accounting for about 9.5% of the project benefits). From an economic perspective, gains are about 27.5% of the total. While the composition for both options assumes a similar path, the Melbourne Metro project’s economic and financial benefits outweigh those of the extended program. To reap optimally, therefore, the former option is...

The aim of the project is to study two of the most widely used machine learning strategies, namely KNearest Neighbours algorithm and Perceptron Learning algorithm, in a quantum setting, and study the speedups that the quantum modules allow over the classical counterparts.

By extracting the information more efficiently and accurately from the test results, machine learning techniques help clinicians get closer to the diagnosis and therefore make better decisions of treatment.

The correlation between the noise threshold used for detecting a galaxy, and the performance of the binary classifier is studied, to study the process of galaxy detection in telescope images.

It is found that the augmentation of the training and testing data has little effect on the accuracy of the models, and this lead to the further investigation of training these physical layers using a TensorFlow Eager model.

Learning is the key to project management, for the reason that much of the success of a project lies in adapting to the changing environment of any project. The key to change lies not in individual learning, but in the learning of the group that integrates the project, what would be called project learning. The objective of this work is to propose a learning project, a project that can adapt to the changing environments that are generated in the project management. Following the proposals of the so-called learning organizations, a “learning project” model is proposed, which is based on four ke...

This study focuses on projects for the development of ML-based service systems in which ML techniques are applied to enterprise functions and proposes a method for collecting insights by referring to a development model based on project practices and developing patterns for ML projects as an enterprise architecture model.

The results illustrate that the project managers in Nepal have a high score in leadership skills, personal characteristics, team development and delegation, communication skills, technical skills, problem-solving/coping with situation skills and stakeholder/relationship management skills.

A method of combining learning algorithms is described that preserves attribute eeciency and yields learning algorithms that require a number of examples that is polynomial in the number of relevant variables and logarithmic in the total number of variables.

This paper expects to lead a writing survey of patterns and techniques for machine learning utilized for the Sensitivity Analysis of the Project Sensitivity analysis to decide the most basic factors that have the best effect on the plausibility and adequacy of the undertaking.

This report outlines various approaches to music composition through Naive Bayes and Neural Network models, and although there were some mixed results by the model, it is evident that musical ideas can be gleaned from these algorithms in hopes of making a new piece of music.

This document reviews IDA and proposes three projects that explore aspects of IDA, which applies IDA to problems in highschool mathematics and investigates whether learning to decompose problems can improve performance over supervised learning.

This paper describes induction motors learning as an important component of electric engineering education. Based on a few years experience this study introduces a new concept of learning in the training field. This concept is implemented by One2One Project. Because teaching in this field relies on electricity and magnetism, energy conversion, AC circuit, measurement method and concepts as well as applied power engineering, students in graduate educational programs find the topics cross-disciplinary, practical, and motivational. The intention of One2one project is double: on one hand, to bring...

The random projection method may be used in conjunction with standard algorithms for a multitude of machine learning tasks, with virtually no degradation in performance, as an alternative to cumbersome nonlinear schemes for dimensionality reduction.

A variety of techniques to improve classification of images and blogs by age and gender for the Machine Learning 2009 competition by adding additional features to Naive Bayes and stemming the dictionary of unique words.

An overview of the challenges in ExCAPE to use supercomputing efficiently with three key examples dealing with ef-cient ML work, support for multi-task learning using matrix factorization methods and the challenges originating from the large and very sparse datasets in Ex CAPE are given.

This method enables us to successfully combine Machine Learning with the Analogous Estimation methodology, thereby boosting the precision of software project estimates for more dependable outcomes.

By generating a model that was able to extract theory-based attributes from the data and connecting this data to an interactive and robust dashboard, new opportunities on working on this data, like showing trend analyses for portfolio management, become available for further research on the promising possibilities of machine-based classification of innovation descriptions.

This paper proposes a different way of debugging an FPGA device which consists in collection of data from FPN ports through an UART connection, processing of data in order to make it readable and affordable for analysis and usage of obtained information for training machine learning models.

Manual analysis of code smells in open-source ML projects showed that code duplication is widespread and that the PEP8 convention for identifier naming style may not always be applicable to ML code due to its resemblance with mathematical notation, but several major obstructions to the maintainability and reproducibility of ML projects were found.

The design and usage of confr is outlined, a concise and flexible configuration system geared towards Python-based machine learning projects that combines some of the capabilities of commonly used systems into a library which aims to reduce repetitive code and maintenance overhead.

A Field-Programmable Gate Array implementation alongside a kernel adaptive filter that is capable of reducing computational resources by introducing a controlled error term, achieving higher modelling capacity for given hardware resources.

Several strategies and examples of entry-level projects are outlined, including mock potential projects using convolutional neural networks toward which the authors can progress, to inspire readers to think outside the box at problem solving using AI and ML.

An algorithmic framework for projected Newton- type methods for solving large-scale optimization problems arising in machine learning and related fields is introduced and how to apply the Newton-type framework to handle non-smooth objectives is shown.

This paper presents a short introduction to the Reservoir Computing and Extreme Learning Machine main ideas and developments, which make use of Neural Networks and Random Projections.

This study opens up an innovative field of research by integrating resources from psychological evaluation and virtual resources to treat various implications of Burnout in school dropout and low academic performance through the analysis of information and the generation of algorithms that allow the projection of burnout risk.

U ovom radu istražuje se prijenosno ucenje kroz vise jezika s ciljem omogucavanja sintakticke analize jezik koji nemaju dovoljno oznacenih poda.

The blog data for this project has already been tokenized, but the data consist of two parts, training vectors and dictionary, which is quite crude.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Machine Learning Developments around the PSQA Project Gera...

It is observed from the previous study that managers spend a lot of time in allocation which is performed according to the experts experience rather than following some specific criteria which lead to inefficient utilization of the resource available, so if a model is developed and trained using machine learning algorithms to handle this routine task so that the manager can spend time in other developmental activities rather than spending time on routine tasks.

This paper reviews appropriate machine learning models for predicate project outcomes and measure project success to see if computers could learn from data.

This paper applies various machine learning algorithms to predict reader reaction to excerpts from the Experience Project to propose a system to process the documents and to predict human reactions, as well as provide results.