Week 9 (23.11.-27.11.) Topic: Deep LearningLessons: Artificial Neural Networks, Backpropagation, Keras, Convolutional Neural Networks, Pretrained Networks, Transfer Learning, Deep Learning PapersProject: Classify images of clothing items with neural networks modelsDataset: Fashion MNISTCode: GitHub This week we dived into Deep Learning and learned about different types neural networks and their applications in various domains. The main... Continue Reading →
Week 8/12 #DataScienceBootcamp
Week 8 (16.11.-20.11.) Topic: Markov SimulationLessons: Markov Chains, Vector & Matrix Multiplication, Python Classes, NumPy Arrays, Program Design, Composition & Inheritance, PEP8 Project: Simulate the paths of new customers in a supermarketDataset: internalCode: GitHub The goal of this project was to create an Markov Chain Monte Carlo (MCMC) simulation of new customers in a supermarket,... Continue Reading →
Week 7/12 #DataScienceBootcamp
Week 7 (09.11.-13.11.) Topic: Data Engineering PipelineLessons: APIs, Docker(-Compose), MongoDB, ETL, Airflow, Logging, Sentiment Analysis, SlackbotProject: Build a pipeline that collects tweets, stores them in a Mongo database, applies sentiment analysis, loads them into a Postgres database, then a Slackbot sends them in a slack channel.Dataset: Tweets collected with the Twitter APICode: GitHub This week's... Continue Reading →
Week 6/12 #DataScienceBootcamp
Week 6 (02.11.-06.11.) Topic: DatabasesLessons: Postgres (from Python), Data Modelling, (Advanced) SQL Queries, Joins & Foreign Keys, (Cloud) Databases, Cloud ComputingProject: Build a dashboard on top of a Postgres database that runs in the AWS cloudDataset: NorthwindCode: GitHub This was another week packed with new information and experiences! In only five days, I managed to... Continue Reading →
Week 5/12 #DataScienceBootcamp
Week 5 (26.10.-30.10.) Topic: Time Series AnalysisLessons: Decomposing Time Series, Naive Forecasts, Evaluating Forecasts, Linear Autoregression, Namespaces, Plotting on Maps, Generators, ARIMA Models, Python ModulesProject: Forecast the temperature in Berlin Mitte and plot climate data on a mapDataset: ecad.euCode: GitHub I found this week's project quite challenging, because I haven't worked with time series and... Continue Reading →
Week 4/12 #DataScienceBootcamp
Week 4 (19.10.-23.10.) Topic: Text ClassificationLessons: Web Scraping, Regular Expression, HTML Parsing, Language Models, Class Imbalance, Bag-of-Words, Naive Bayes, Python Functions, Command Line InterfaceDataset: Self web-scraped song lyricsProject: Predict the artist from song lyrics.Code: GitHub I was super excited about this week, because it was about language models and first steps into NLP, my favorite... Continue Reading →
Week 3/12 #DataScienceBootcamp
Week 3 (12.10.-16.10.) Topic: Machine Learning - RegressionLessons: Linear Regression, Feature Expansion, Gradient Descent, Regularization, Feature Selection, Hyperparameter Optimization, Gradient Boosting, Debugging.Dataset: Capital BikeshareProject: Predict demand for bicycle rentals at any given hour, based on time- and weather-related features (and submit the predictions in the kaggle competition).Code: GitHub I really enjoyed this week's project for... Continue Reading →
Week 2/12 #DataScienceBootcamp
Week 2 (05.10.-09.10.) Topic: Machine Learning - ClassificationLessons: ML workflow, Logistic Regression, Feature Engineering, Decision Trees, Random Forests, Evaluating Classifiers, Cross-Validation, Loss FunctionDataset: TitanicProject: Predict passenger survival on the Titanic and submit the model to the kaggle competition. On the second week of the bootcamp, we started with Machine Learning (ML). If you think about... Continue Reading →
Week 1/12 #DataScienceBootcamp
September 28th, 2020 - the end of a month, the beginning of a new challenge: Today I start the Data Science Bootcamp at Spiced Academy in Berlin. For the next 12 weeks, I'll be learning about machine learning, NLP, data infrastructure, and software engineering, work on different small projects, and present my final big project... Continue Reading →
5 eye-opening books about ethics in Artificial Intelligence
Artificial Intelligence is undoubtedly an exciting field. We are making machines think like humans, mimic our actions, and solve problems more efficiently than us, at this at an unprecedented level and speed. But beyond the hype, I can't help but wonder: does more efficiently mean better? Are some of our actions worthy of being mimicked?... Continue Reading →
