Pinned Repositories
dcgan-fake-faces
Deep convolutional generative adversarial networks (DCGANs) for generating fake faces with Tensorflow and Keras.
DD2434-VAE-Project
Replication of the research paper titled Auto-Encoding Variational Bayes.
hmm
Hidden Markov Models (HMMs) for estimating the sequence of hidden states (decoding) via the Viterbi algorithm, and estimating model parameters (learning) via the Baum- Welch algorithm.
hopfield-networks
Implementing Hopfield Networks from scratch, testing their content addressable memory, attractor, and energy landscape, investigating their resistance to noise, experimenting with their memory capacity, and putting strain on them with sparse patterns.
nn-blocks
A neural network library built from scratch, without dedicated deep learning packages. Training and testing deep neural networks and utilizing deep learning best practices for multi-class classification with fully connected neural networks, text generation with recurrent neural networks, and regression with fully connected networks.
pca-mds-isomap
Dimensionality reduction and data embedding via PCA, MDS, and Isomap.
re-sln
Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.
slp-mlp
Single Layer Perceptrons (SLPs) and Multi-Layer Perceptrons (MLPs) from scratch, only with numpy, for classification and regression. MLPs with Keras for time-series prediction.
som
Kohonen Self-Organizing Maps (SOMs) for dimensionality reduction, data embedding, and solving a variant of the travelling salesman problem.
variational-inference-gmm
Coordinate ascent mean-field variational inference (CAVI) using the evidence lower bound (ELBO) to iteratively perform the optimal variational factor distribution parameter updates for clustering.
mark-antal-csizmadia's Repositories
mark-antal-csizmadia/hopfield-networks
Implementing Hopfield Networks from scratch, testing their content addressable memory, attractor, and energy landscape, investigating their resistance to noise, experimenting with their memory capacity, and putting strain on them with sparse patterns.
mark-antal-csizmadia/variational-inference-gmm
Coordinate ascent mean-field variational inference (CAVI) using the evidence lower bound (ELBO) to iteratively perform the optimal variational factor distribution parameter updates for clustering.
mark-antal-csizmadia/DD2434-VAE-Project
Replication of the research paper titled Auto-Encoding Variational Bayes.
mark-antal-csizmadia/hmm
Hidden Markov Models (HMMs) for estimating the sequence of hidden states (decoding) via the Viterbi algorithm, and estimating model parameters (learning) via the Baum- Welch algorithm.
mark-antal-csizmadia/nn-blocks
A neural network library built from scratch, without dedicated deep learning packages. Training and testing deep neural networks and utilizing deep learning best practices for multi-class classification with fully connected neural networks, text generation with recurrent neural networks, and regression with fully connected networks.
mark-antal-csizmadia/pca-mds-isomap
Dimensionality reduction and data embedding via PCA, MDS, and Isomap.
mark-antal-csizmadia/rbm_dbn
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks (DBNs) from scratch for representation learning on the MNIST dataset.
mark-antal-csizmadia/re-sln
Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.
mark-antal-csizmadia/som
Kohonen Self-Organizing Maps (SOMs) for dimensionality reduction, data embedding, and solving a variant of the travelling salesman problem.
mark-antal-csizmadia/dcgan-fake-faces
Deep convolutional generative adversarial networks (DCGANs) for generating fake faces with Tensorflow and Keras.
mark-antal-csizmadia/discovery-of-frequent-itemsets-and-association-rules
Discovery of Frequent Itemsets and Association Rules with the Apriori algorithm. Made with Python and PySpark.
mark-antal-csizmadia/slp-mlp
Single Layer Perceptrons (SLPs) and Multi-Layer Perceptrons (MLPs) from scratch, only with numpy, for classification and regression. MLPs with Keras for time-series prediction.
mark-antal-csizmadia/variational-inference
Factorized variational approximation using a univariate Gaussian distribution over a single variable x.
mark-antal-csizmadia/eigenfaces
Eigenfaces exercise. Started from here with ML.
mark-antal-csizmadia/em-simple
Expectation Maximization (EM) algorithm for estimating maximum likelihood (ML) parameters of partially observed data on a three-node Bayesian Network Probabilistic Graphical Model.
mark-antal-csizmadia/finding-similar-items-textually-similar-documents
Finding Similar Items: Textually Similar Documents
mark-antal-csizmadia/gitignore
A collection of useful .gitignore templates
mark-antal-csizmadia/graphx-network-analysis
Analyzing product co-purchasing networks as graphs.
mark-antal-csizmadia/hadoop-mapreduce-hbase-basics
Basic applications with Hadoop MapReduce and HBase.
mark-antal-csizmadia/hyperball-hyperloglogcounters
Implementation of the HyperBall algorithm with HyperLogLogCounters from the paper titled "In-Core Computation of Geometric Centralities with HyperBall: A Hundred Billion Nodes and Beyond".
mark-antal-csizmadia/mark-antal-csizmadia
GitHub profile readme
mark-antal-csizmadia/mark-antal-csizmadia..github.io
GitHub IO page.
mark-antal-csizmadia/naive_cnn
Naive implementation of Convolution Neural Networks (CNNs). Example architecture LeNet5 on MNIST hand-written digits.
mark-antal-csizmadia/personal-website
My personal website built with Django. An absolute overkill ... but good practice. Will set up a normal portfolio website with Github pages.
mark-antal-csizmadia/shields
Concise, consistent, and legible badges in SVG and raster format
mark-antal-csizmadia/spark-basics
Basics with Spark via PySpark.
mark-antal-csizmadia/spectral-clustering
Re-implementation of the paper titled "On Spectral Clustering: Analysis and an algorithm" by AY Ng et al.
mark-antal-csizmadia/svm
Support Vector Machines (SVMs) from scratch, without dedicated packages, for the classification of linear and non-linear data.