Refine
Document Type
- Master's Thesis (4) (remove)
Year of publication
- 2019 (4) (remove)
Language
- English (4)
Keywords
- Maschinelles Lernen (4) (remove)
Institute
A relatively new research field of neurosciences, called Connectomics, aims to achieve a full understanding and mapping of neural circuits and fine neuronal structures of the nervous system in a variety of organisms. This detailed information will provide insight in how our brain is influenced by different genetic and psychiatric diseases, how memory traces are stored and ageing influences our brain structure. It is beyond question that new methods for data acquisition will produce large amounts of neuronal image data. This data will exceed the zetabyte range and is impossible to annotate manually for visualization and analysis. Nowadays, machine learning algorithms and specially deep convolutional neuronal networks are heavily used in medical imaging and computer vision, which brings the opportunity of designing fully automated pipelines for image analysis. This work presents a new automated workflow based on three major parts including image processing using consecutive deep convolutional networks, a pixel-grouping step called connected components and 3D visualization via neuroglancer to achieve a dense three dimensional reconstruction of neurons from EM image data.
Neural networks have become one of the most powerful algorithms when it comes to learning from big data sets and it is used extensively for classification. But the deeper the network models, the lesser is the interpretability of such models. Although many methods exist to explain
the output of such networks, the lack of interpretability makes them black boxes. On the other hand, prototype-based machine learning algorithms are known to be interpretable and robust.
Therefore, the aim of this thesis is to find a way to interpret the functioning of the neural networks by introducing a prototype layer to the neural network architecture. This prototype layer will train alongside the neural network and help us interpret the model. We present architectures of neural networks consisting of autoencoders and prototypes that perform activity recognition from heart rates extracted from ECG signals. These prototypes represent the different activity groups that the heart rates belong to and thereby aid in interpretability.
Many companies use machine learning techniques to support decision-making and automate business processes by learning from the data that they have. In this thesis we investigate the theory behind the most widely used in practice machine learning algorithms for solving classification and regression problems.
In particular, the following algorithms were chosen for the classification problem: Logistic Regression, Decision Trees, Random Forest, Support Vector Machine (SVM), Learning Vector Quantization (LVQ). As for the regression problem, Decision Trees, Random Forest and Gradient Boosted Tree were used. We then apply those algorithms to real company data and compare their performances and results.
Prototype-based classification methods like Generalized Matrix Learning Vector Quantization (GMLVQ) are simple and easy to implement. An appropriate choice of the activation function plays an important role in the performance of (deep) multilayer perceptrons (MLP) that rely on a non-linearity for classification and regression learning. In this thesis, successful candidates of non-linear activation functions are investigated which are known for MLPs for application in GMLVQ to realize a non-linear mapping. The influence of the non-linear activation functions on the performance of the model with respect to accuracy, convergence rate are analyzed and experimental results are documented.