#nodejs

• Building a NodeJS express backend with TypeScript

• MakeEvents App with NodeJS backend and an Angular frontend

#backend

• Building a NodeJS express backend with TypeScript

• MakeEvents App with NodeJS backend and an Angular frontend

• Building a Spring Boot application using Java

#typescript

• Building a NodeJS express backend with TypeScript

• MakeEvents App with NodeJS backend and an Angular frontend

#expressjs

• Building a NodeJS express backend with TypeScript

• MakeEvents App with NodeJS backend and an Angular frontend

#frontend

• MakeEvents App with NodeJS backend and an Angular frontend

#angular

• MakeEvents App with NodeJS backend and an Angular frontend

• Twitter data - an interactive visualization and location prediction

#books

• List of 50 books for the upcoming year

#goal

• List of 50 books for the upcoming year

#reading

• List of 50 books for the upcoming year

#fun

• List of 50 books for the upcoming year

#java

• Building a Spring Boot application using Java

• Started reading Effective Java (3rd edition) by Joshua Bloch

#spring

• Building a Spring Boot application using Java

#rest

• Building a Spring Boot application using Java

#docker

• Building a Spring Boot application using Java

#knowledge

• Started reading Effective Java (3rd edition) by Joshua Bloch

• How to squash commits properly

• The first baby-steps in data scince

• Using KNN algorithm to estimate photometric redshifts

#git

• How to squash commits properly

#datascience

• The first baby-steps in data scince

• Using KNN algorithm to estimate photometric redshifts

• Photometric redshift estimation 1.

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Photometric redshift estimation 2.

• Linear methods in classification

• Photometric redshift estimation 3.

• Photometric redshift summary

• Image classification using machine learning on MNIST dataset

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

• DBSCAN clustering on human brain cell data

• Tree based classification on Titanic data

• CNN on the CIFAR-100 dataset, naive approaches

• T-SNE algorithm and various data related problems

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Twitter data - an interactive visualization and location prediction

• Deep learning on the MNIST dataset using the Keras API

• Exploratory data analysis of streams in the USA

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

• Text generation using basic RNN architecture - Tensorflow tutorial

• Stacked boosting for photo-z estimation - a university Kaggle challenge

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

#python

• The first baby-steps in data scince

• Using KNN algorithm to estimate photometric redshifts

• Photometric redshift estimation 1.

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Photometric redshift estimation 2.

• Linear methods in classification

• Photometric redshift estimation 3.

• Photometric redshift summary

• Image classification using machine learning on MNIST dataset

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

• DBSCAN clustering on human brain cell data

• Tree based classification on Titanic data

• CNN on the CIFAR-100 dataset, naive approaches

• T-SNE algorithm and various data related problems

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Twitter data - an interactive visualization and location prediction

• Deep learning on the MNIST dataset using the Keras API

• Exploratory data analysis of streams in the USA

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

• Text generation using basic RNN architecture - Tensorflow tutorial

• Stacked boosting for photo-z estimation - a university Kaggle challenge

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

#scikit

• The first baby-steps in data scince

#clustering

• The first baby-steps in data scince

• DBSCAN clustering on human brain cell data

• Tree based classification on Titanic data

#classification

• Using KNN algorithm to estimate photometric redshifts

• Photometric redshift estimation 1.

• Photometric redshift estimation 2.

• Linear methods in classification

• Image classification using machine learning on MNIST dataset

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

#sklearn

• Using KNN algorithm to estimate photometric redshifts

• Photometric redshift estimation 1.

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Photometric redshift estimation 2.

• Linear methods in classification

• Image classification using machine learning on MNIST dataset

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

• DBSCAN clustering on human brain cell data

• Tree based classification on Titanic data

• CNN on the CIFAR-100 dataset, naive approaches

• T-SNE algorithm and various data related problems

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Twitter data - an interactive visualization and location prediction

• Deep learning on the MNIST dataset using the Keras API

#astronomy

• Photometric redshift estimation 1.

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Photometric redshift estimation 2.

• Photometric redshift estimation 3.

• Photometric redshift summary

#statsmodels

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Linear methods in classification

#regression

• Photometric redshift estimation with statsmodels, scikit-learn and naive linear regression implementation using numpy

• Linear methods in classification

• Image classification using machine learning on MNIST dataset

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

#mnist

• Image classification using machine learning on MNIST dataset

• T-SNE algorithm and various data related problems

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Deep learning on the MNIST dataset using the Keras API

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#ridge

• Getting acquainted with different regression models using scientific data from different sources

#lasso

• Getting acquainted with different regression models using scientific data from different sources

#aic

• Getting acquainted with different regression models using scientific data from different sources

#bic

• Getting acquainted with different regression models using scientific data from different sources

#statistics

• Getting acquainted with different regression models using scientific data from different sources

• Logistic regression and SVM classification on famous Titanic data from Kaggle

#decisiontree

• Tree based classification on Titanic data

#googleMLtutorial

• Tree based classification on Titanic data

#CNN

• CNN on the CIFAR-100 dataset, naive approaches

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Deep learning on the MNIST dataset using the Keras API

#google

• CNN on the CIFAR-100 dataset, naive approaches

#colab

• CNN on the CIFAR-100 dataset, naive approaches

#t-sne

• T-SNE algorithm and various data related problems

#perceptron

• Perceptron and their model with the implementation of the multi layer perceptron by hand

#keras

• Perceptron and their model with the implementation of the multi layer perceptron by hand

• Deep learning on the MNIST dataset using the Keras API

#twitter

• Twitter data - an interactive visualization and location prediction

#leafletJS

• Twitter data - an interactive visualization and location prediction

#deeplearning

• Deep learning on the MNIST dataset using the Keras API

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

• Text generation using basic RNN architecture - Tensorflow tutorial

#analysis

• Exploratory data analysis of streams in the USA

#visualization

• Exploratory data analysis of streams in the USA

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

#tensorflow

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

• Text generation using basic RNN architecture - Tensorflow tutorial

• Neural Style Transfer

#neuralnetwork

• Variational autoencoder on the CIFAR-10 dataset 1.

• Variational autoencoder on the CIFAR-10 dataset 2.

• Text generation using basic RNN architecture - Tensorflow tutorial

#autoencoder

• Variational autoencoder on the CIFAR-10 dataset 2.

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#rnn

• Text generation using basic RNN architecture - Tensorflow tutorial

• How does a recurrent neural network actually work? An implementation guide with detailed math

#tf_data

• Text generation using basic RNN architecture - Tensorflow tutorial

#MIT

• Text generation using basic RNN architecture - Tensorflow tutorial

#machine learning

• Stacked boosting for photo-z estimation - a university Kaggle challenge

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Neural Style Transfer

• Neural nets from scratch

• Glia cell detection using FAIR's Detectron framework

• UNET architecture on multi-gpu for pathological image analysis

• How does a recurrent neural network actually work? An implementation guide with detailed math

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

• Generative adversarial networks

• Fast neural style transfer

• Fast neural style transfer II.

• Graph representation learning - node embedding algorithms

• Fast neural style transfer III.

• Training RoBERTa and Reformer with Huggingface

#boosting

• Stacked boosting for photo-z estimation - a university Kaggle challenge

#ensemble

• Stacked boosting for photo-z estimation - a university Kaggle challenge

#deep learning

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Neural Style Transfer

• Neural nets from scratch

• Glia cell detection using FAIR's Detectron framework

• UNET architecture on multi-gpu for pathological image analysis

• How does a recurrent neural network actually work? An implementation guide with detailed math

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

• Generative adversarial networks

• Fast neural style transfer

• Fast neural style transfer II.

• Graph representation learning - node embedding algorithms

• Fast neural style transfer III.

• Training RoBERTa and Reformer with Huggingface

#wigner-csnl

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

#cifar10

• Autoencoders on different datasets - neuroscience

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#vae

• Almost variational autoencoders on different datasets - neuroscience (2.)

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#research

• Almost variational autoencoders on different datasets - neuroscience (2.)

#network theory

• Network theory - fundementals I.

• Network theory - models II.

• Network theory - models III.

#physics

• Network theory - fundementals I.

• Network theory - models II.

• Network theory - models III.

#mathematics

• Network theory - fundementals I.

• Network theory - models II.

• Network theory - models III.

#lecture notes

• Network theory - fundementals I.

• Network theory - models II.

• Network theory - models III.

#neural networks

• Neural Style Transfer

• Neural nets from scratch

• Glia cell detection using FAIR's Detectron framework

• UNET architecture on multi-gpu for pathological image analysis

• How does a recurrent neural network actually work? An implementation guide with detailed math

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

• Generative adversarial networks

• Fast neural style transfer

• Fast neural style transfer II.

• Graph representation learning - node embedding algorithms

• Fast neural style transfer III.

• Training RoBERTa and Reformer with Huggingface

#numpy

• Neural nets from scratch

#cpp

• Neural nets from scratch

#software design

• Neural nets from scratch

#backpropagation

• Neural nets from scratch

#pathology

• Glia cell detection using FAIR's Detectron framework

• UNET architecture on multi-gpu for pathological image analysis

#unet

• UNET architecture on multi-gpu for pathological image analysis

#recurrent neural network

• How does a recurrent neural network actually work? An implementation guide with detailed math

#lvae

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#bayesian learning

• Variational autoencoders I.- MNIST, Fashion-MNIST, CIFAR10, textures

#gan

• Generative adversarial networks

#style transfer

• Fast neural style transfer

• Fast neural style transfer II.

• Fast neural style transfer III.

#fast neural style transfer

• Fast neural style transfer

• Fast neural style transfer II.

• Fast neural style transfer III.

#+ detectron2 + deep learning + neural networks + machine learning + pathology

• Glia cell detection using FAIR's Detectron2 framework

#+ regression + logistic regression + binary classification + machine learning

• Logistic regression

#+ classification + logistic regression + binary classification + machine learning

• Neural networks from scratch rebooted

#+ deep learning + hamiltonian mechanics + physics + neural networks

• Hamiltonian neural networks

#+ deep learning + class activation mapping + deepdream + feature visualization + neural networks

• Visualizing neural networks I.

• Visualizing neural networks II.

#+ deep learning + autoregressive models + pixelcnn + neural networks + mixture models

• Autoregressive models - PixelCNN

#graph representation learning

• Graph representation learning - node embedding algorithms

#node embedding

• Graph representation learning - node embedding algorithms

#multi-style

• Fast neural style transfer III.

#fast-stylization

• Fast neural style transfer III.

#conditional instance normalization

• Fast neural style transfer III.

#+ deep learning + contrastive learning + simclr + deep learning + unsupervised learning

• SimCLR - simple contrastive learning

#nlp

• Training RoBERTa and Reformer with Huggingface

#language modeling

• Training RoBERTa and Reformer with Huggingface

#reformer

• Training RoBERTa and Reformer with Huggingface

#transformers

• Training RoBERTa and Reformer with Huggingface

#attention

• Training RoBERTa and Reformer with Huggingface

#+ deep learning + capsule network + dynamic routing + multimnist + image classification

• Capsule Networks - a 'new' way of thinking

#+ deep learning + loss function + visualization + optimization + image classification

• Visualizing the loss landscape