It's AI Against Corona

2019-nCoV

There has been a lot of talking about the new corona virus going around the world. Let's clear up some things about it first and then we will see how data science and ai can help us fight 2019-nCoV.

Activation Functions

What are activation functions in Neural Networks?

First of all let's clear some terminology you need in order to understand the concept of an activation function.

Backpropagation

or backward propagation of errors

is another supervised learning optimization algorithm. The main task of the backpropagation algorithm is to find optimal weights in a by implementing optimization technique.

CNNs

The Convolutional Neural Network

(CNN) architecture is widely used in the field of computer vision. Because we have a massive amount of data in image files, the usage of traditional neural networks wouldn't give much efficiency as the computational time would explode.

This article assumes, you have basic knowledge about neural networks and matrix manipulation. In case you need a refresher on these topics, check out the following links:

Early Stopping

In this article

we will introduce you to the concept of Early Stopping and its implementation including code samples.

GAN

Generative Adversarial Networks

(GANs) are a type of unsupervised neural networks. The network exists since 2014 and was developed by and colleges.

Gradient Descent

Hiking Down a Mountain

Gradient Descent is a popular optimization technique in machine learning. It is aimed to find the minimum value of a function.

Introduction to Statistics

Part III

In this third and last part of the series "Introduction to Statistics" we will cover questions as what is probability and what are its types, as well as the three probability axioms on top of which the entire probability theory is constructed.

Introduction to Statistics

Part I

In the following three parts we will cover basic terminology as well as the core concepts from statistics. In this Part I you are going to learn about measures of central tendency (mean, median and mode). In the Part II you will read about measures of variability and different distributions. Finally, in the last Part III you will get to know types of probability such as marginal, joint and conditional. Enjoy!

Introduction to Statistics

Part II

In this part we will continue our talk about descriptive statistics and the measures of variability such as range, standard deviation and variance as well as different types of distributions. Feel free to read the Part I of these series to deepen your knowledge about the measures of central tendency:

Logistic Regression

Logit Regression

Logit regression is another shortened name derived from logistic unit. Logistic regression is a popular statistical model that generates probabilities for binary classification tasks. It produces discrete values and its span lies in the range of [0.0 ; 1.0]. A discrete value is some outcome (dependent variable) that has only a limited number of possible values.

Loss Functions

When training a neural network,

we try to optimize the algorithm, so it gives the best possible output. This optimization needs a loss function to compute the error/loss of the model.

In this article we will gain a general picture of Squared Error, Mean Squared Error (MSE), Maximum Likelihood Estimation (MLE) and Cross Entropy.

The Magic Behind Tensorflow

Getting started

In this article we will delve into the magic behind one of the most popular Deep Learning frameworks - Tensorflow. We will look at the crucial terminology and some core computation principles we need to grasp the real power of Tensorflow.

Classification with Naive Bayes

The Bayes' Theorem

describes the probability of some event, based on some conditions that might be related to that event.

Neural Networks

Neural Networks - Introduction

In Neural Networks (NNs) we try to create a program which is able to learn from experience with respect to some task. This program should consider a performance measure, if its performance improves with experience.

PCA

Principal component analysis

or PCA is a technique for taking out relevant data points (variables also called components or sometimes features) from a larger data set. From this high dimensional data set, PCA tries extracting low dimensional data points. The idea is that with PCA we would be able to reproduce as much information as feasible in a low-dimensional space. If we have less variables, the data visualization becomes easier to understand. PCA is often used in problems, where we have to work with higher dimensions in data.

Introduction to reinforcement learning

Part IV: Policy Gradient

In the previous articles from this series on Reinforcement Learning (RL) we discussed Model-Based and Model-Free RL. In model-free RL we talked about Value Function Approximation (VFA). In this Part we are going to learn about Policy Based Reinforcement Learning, specifically about policy gradient methods.

Introduction to Reinforcement Learning

Part I : Model-Based Reinforcement Learning

Welcome to the series "Introduction to Reinforcement Learning" which will give you a broad understanding about basic (and not only :) ) techniques in the field of Reinforcement Learning. The article series assumes you have some basic knowledge about and Machine Learning in general.

In Part I of these series we will learn about model-based Reinforcement Learning methods, including Dynamic Programming : policy and value iteration algorithms, Markov Processes, the Bellman Equation and much more ... ;)

Introduction to Reinforcement Learning

Part II : Model-Free Reinforcement Learning

In this Part II we're going to deal with Model-Free approaches in Reinforcement Learning (RL). See what model-free prediction and control mean and get to know some useful algorithms like Monte Carlo (MC) and Temporal Difference (TD) Learning.

In Part I of this series we've already learned about Model-Based Reinforcement Learning (RL). Please refer to Part I to get acquainted with the basics.

Recurrent Neural Networks

RNNs

A Recurrent Neural Network (RNN) is a type of neural network where an output from the previous step is given as an input to the current step. RNNs are designed to take an input series with no size limits. RNNs remember the past states and are influenced by them. This type of are well suited for time series data.

SVM

Support Vector Machines

If you happened to have a classification, a regression or an outlier detection task, you might want to consider using Support Vector Machines (SVMs), a supervised learning model, that builds a line (hyperplane) to separate data into groups. SVM can perform not only linear classification but also effectively separate data in a non-linear, multi-dimensional space using the so called kernel trick which transfers data points into a high dimensional space. SVM is no new special fancy technique for machine learning, it exists since 1963.

Despite the fact that SVM is also applied for regression tasks, it is still more often used for classification.

Singular Value Decomposition

Matrix factorization: Singular Value Decomposition

Matrix decomposition is another name for matrix factorization. This method is a nice representation for applied linear algebra in machine learning and similar algorithms.

Partial Derivatives and the Jacobian Matrix

A Jacobian Matrix

is a special kind of matrix that consists of first order partial derivatives for some vector function. The form of the Jacobian matrix can vary. That means, the number of rows and columns can be equal or not, denoting that in one case it is a square matrix and in the other case it is not.

Introduction to Reinforcement Learning

Part III: Value Function Approximation

In the previous Part I and Part II of this series we described model-based and model-free reinforcement learning as well as some well known algorithms. In this Part III we are going to talk about Value Function Approximation: what it is and how it can be helpful in the world of Reinforcement Learning (RL).

Weight Initialization

How does Weight Initialization work?

As a general rule, weights and biases are normally initialized with some random numbers. Weights and biases are extremely important model's parameters and play a pivot role in every neural network training. Therefore, one should have a firm understanding of how they work and why one needs them. In this article we will see how we can initialize and optimize weights to achieve better performance in a neural network.

Word Embeddings

Part 1: Introduction to Word2Vec

Word embedding is a popular vocabulary representation model. Such model is able to capture contexts and semantics of a word in a document. So what is it exactly?

Word Embeddings

Part 2: Word2Vec (Skip Gram)

In the second part of Word Embeddings we will talk about what are the downsides of the Word2Vec model (Skip Gram in particular).

t-SNE

T-Distributed Stochastic Neighbor Embedding

If you do data analysis, machine learning or some other data driven research you will probably encounter with high dimensional data. High dimensions in a data set mean that we have a high number of features (sometimes also called input variable). Our goal is to find good feature values and use them in our model training.

In this article, we will talk about a dimensionality reduction technique known as T-Distributed Stochastic Neighbor Embedding or t-SNE for short.