Intro and Overview Machine Learning Lecture
Contents
Intro and Overview Machine Learning Lecture#
Author: Prof. Dr. Johannes Maucher
Email: maucher@hdmstuttgart.de
Last Update: October, 4th 2021
Goals of this Lecture#
Goals of this lecture are:
Understand the basic concepts, procedures and categories of Machine Learning
For any task or problem: Know, which algorithmtype is suitable for this task
Understand conventional MLalgorithms
Understand Deep Learning
Understand the currently most important types of Deep Neural Networks
Implementations are provided in order to support understanding
Contents#
Intro#
Basic Concepts of Data Mining and Machine Learning
Definition
Categories
Validation
Conventional ML Algorithms#
Neural Networks and Deep Neural Networks#

Natural Neuron
General Notions for Artificial Neural Networks
Single Layer Perceptron (SLP)
Architectures for Regression and Classification
Gradient Descent and Stochastic Gradient Descent Learning
Gradient Descent and Stochastic Gradient Descent Learning
Multilayer Perceptron (MLP) Architectures for Regression and Classification
BackpropagationAlgorithm for Learning
Recurrent Neural Networks (RNN)
Simple Recurrent Neural Networks (RNNs)
Long shortterm Memory Networks (LSTMs)
Gated Recurrent Units (GRUs)
Application Categories of Recurrent Networks
Deep Neural Networks: Convolutional Neural Networks (CNN)
Overall Architecture of CNNs
General concept of convolution filtering
Layertypes of CNNs:
Convolution,
Pooling,
FullyConnected
MLP and CNN for Object Classification
Example Data: Cifar10 Image Dataset
Image Representation in numpy
Define, train and evaluate MLP in Keras
Define, train and evaluate CNN in Keras
Apply pretrained CNNs for object classification  original task
Access image from local file system
Download and apply pretrained CNNs for object recognition in arbitrary images

Download pretrained featureextractor (CNN without the classifier part)
Define new classifier architecture and concatenate it with pretrained classifier
Finetune network with taskspecific data
Apply the finetuned network for objectrecognition
Autoencoder#
GAN#
Reinforcement Learning#
Modelling of Text#
Modelling of Words and Texts / Word Embeddings
Concept of WordEmbeddings
SkipGram and CBOW
Working with pretrained wordembeddings
Text Classification with CNNs and LSTMs
Example Data: IMDBMovie Reviews for Sentiment Classification
Text preprocessing and representation with Keras
Load and apply pretrained wordembedding
News classification with CNN
News classification with LSTM
Graph Neural Networks#

Concepts of GNNs
Implementation of GNN with Keras
Document Classification with GNNs