## Autoencoders

[Download this notebook](12 - Autoencoders.ipynb) I did my best to minimize the training time. I had saved a model that was trained already. However, the server does not play along. Therefore it is best to just do something else for an hour when training. You don’t have to train 100 epochs, you can end the training early via Kernel > Interrupt Kernel. In this lesson you’ll learn: what an autoencoder is.

## Bayesian Linear Regression

Download this notebook This notebook shows the advantage of Bayesian Linear Regression vs. regular Least-Squares-Estimation-based Linear Regression with respect to outliers. The Bayesian part of the approach shown here is that the error’s/noise’s standard deviation $\sigma$ is now not necessarily constant, but a random variable, too, bounded by a lower bound $\sigma_0$ and an upper bound $\infty$. Standard Linear Regression Assumption: f(x) = a + bx with measurement $y_i = f(x_i) + \epsilon_i$ with $\epsilon_i \sim \mathcal{N}\left(0,\sigma_0^2\right)$.

## Bootstrapping

Download this notebook There is a story about a man who got stuck in quicksand and would have suffered a horrible death, but he managed to pull himself out of the sand by his boot straps. In German, Baron von Münchhausen had a similar story about how he pulled himself out of a swamp by his hair. Obviously, all of this is nonsense, but it coined the name of a statistical method - Bootstrapping - that seems to be similarly ludicrous, but actually works and is insanely useful for many otherwise difficult situations.

## Clustering basics

Download this notebook This ipynb is based on a workshop organised by the tech consulting company TNG. The notebook explains the theoretical background of three widely used clustering algorithms and uses them on some sample data. As a final example, clusters are used to ‘‘discretise’’ the colours of an image. import numpy as np import seaborn as sns import matplotlib import matplotlib.pyplot as plt #from plotting_utilities import * from sklearn.datasets import make_moons, make_blobs from sklearn.

## CNN & Transfer Learning

[Download this notebook](10 - Transfer Learning.ipynb) In this lesson you’ll learn: what is meant by transfer learning. how to load and customize pre-trained models. how to read images from folders into Python. Last week you developed a CNN that can recognize numbers. Today, we focus on taking advantage of pre-trained neural networks. First, you will train a model that can distinguish between various breeds of dogs and cats. In the training task, you will use ResNet to detect pneumonia in X-ray images.

## Convolutional Neural Network

[Download this notebook](09 - Convolutional Neural Network.ipynb) This week we are looking at convolutional neural networks. Convolutional neural networks (CNNs) are used primarily, but not exclusively, for image recognition. Unlike the neural networks we have seen so far, CNNs can read images as a matrix. This means that local context is not lost by flattening the image. Otavio Good. 2017 “A Visual and Intuitive Understanding of Deep Learning” O’Reilly AI Conference import torch from torch import nn import pandas as pd import numpy as np from matplotlib import pyplot as plt from torch.

## Data Science - Toxicological Predictions

[Download this notebook](05 - Data Science.ipynb) In this lesson you’ll learn: how to train a SVM. why it is necessary to scale variables. how to train a random forest model. about Y-scrambling and the necessity of train/test splits. how to split data into a training set and test set. Today you will learn some basics of data science and machine learning. These will also be relevant for training neural networks. As an example, we will build models to detect the toxicological concern of molecules.

## Deep Q Learning with Pytorch

Download this notebook Author: Oliver Mai As presented in this YouTube video by Phil Tabor Gym Environment: LunarLander-v2 This environment is inspired by a subfield of Optimal Control: rocket trajectory optimization. Sadly the documentation is a bit lacking, but we will briefly talk about features of this environment. In “LunarLander-v2” the agent (or human player) controls a spacecraft, which is supposed to be landed on a planetary surface. The lander can only be moved in a 2D plane (Note: This environment requires the 2D physics engine “Box2d”, which can be installed by pip install -e '.

## Encoding

Download this notebook Many ML models struggle with categorical input data, because they expect numeric input data. This notebook will present three methods to transform categorical into numeric data through a process called “encoding”: label encoding, ordinal encoding and one-hot encoding. Warning: You should probably encode the full data set before doing a train-test-split. Otherwise, you may accidentally assign two different encoding schemes to the training and test data which will then, of course, cause trouble for the ML model.

## First Neuronal Network

[Download this notebook](07 - First Neural Net.ipynb) In this lesson you’ll learn: how one-hot encoding works. how to program a simple neural net in Python. Before we train the neural network, the first thing we need to do is load the relevant libraries and functions. import numpy as np from matplotlib import pyplot as plt %matplotlib inline Activation functions def sigmoid(x): return 1 / (1 + np.exp(-x)) # np.exp() = e^() def softmax(x, axis=1): return np.