Tim Sainburg

noisereduce. Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

tensorflow2-generative-models. Implementations of a number of generative models in Tensorflow 2. GAN, VAE, Seq2Seq, VAEGAN, GAIA, Spectrogram Inversion. Everything is self contained in a jupyter notebook for easy export to colab.

Tensorflow-MultiGPU-VAE-GAN. A single jupyter notebook multi gpu VAE-GAN example with latent space algebra and receptive field visualizations.

python_spectrograms_and_inversion. Spectrograms, MFCCs, and Inversion Demo in a jupyter notebook

ParametricUMAP_paper. Parametric UMAP embeddings for representation and semisupervised learning. From the paper "Parametric UMAP: learning embeddings with deep neural networks for representation and semi-supervised learning" (Sainburg, McInnes, Gentner, 2020).

GAIA. Generative Adversarial Interpolative Autoencoder (GAIA) is a Generative Adversarial Network (GAN) made up of Autoencoders (AE) trained explicitly on interpolations to promote convexity and better latent interpolations.

AVGN. A generative network for animal vocalizations. For dimensionality reduction, sequencing, clustering, corpus-building, and generating novel 'stimulus spaces'. All with notebook examples using freely available datasets.

avgn_paper. Latent and generative models of animal vocalizations for songbirds, mice, primates, humans, cetaceans, etc.

tensorflow-2-feature-visualization-notebooks. Feature and class visualization with deep neural networks in tensorflow. Contains deepdream, style transfer, receptive field visualization, convolutional filter visualization, etc.

vocalization-segmentation. Simple python algorithms for segmenting animal (songbird, mice) vocalizations into notes and syllables using Dynamic Thresholding and Continuity Filtering.

birdbrain. A library for viewing songbird brain atlases (European starling, Canary, Zebra finch, Pigeon, Mustached bat)

curriculum_vitae. My Curriculum Vitae, generated in Python via Jinja from JSON fields into HTML. http://timsainburg.com/pages/cv.html

postdoc_salaries. Jupyter Notebook

automutualinformation. Auto Mutual Information (Sequential Mutual Information) for temporal data.

neuroethology_paper_2021. for 2021 current opinions paper

ParallelsBirdsongLanguagePaper. Code for the Paper "Parallels in the sequential organization of birdsong and human speech." Nature Communications (2019)

multicam_airflow_pipeline. Multicamera analysis pipeline in Apache Airflow

multicamera_labelling_and_training. Code to generate labelling sets, training sets, and train 2D/3D keypoint networks in mmpose/mmdetection.

kinectacq. Acquisition from a Kinect rig

graph_research_notes. Graphing my grad school research notes using networkx and sigma.js

visualize_wordpress_posts. Visualizing Wordpress Posts using D3 forced directed networks

cdcp_paper. Code for the paper "Expectation-driven sensory adaptations support enhanced acuity during categorical perception" (Nature Neuroscience)

LongRangeSequentialOrgPaper. Jupyter Notebook

spikesorting-graph-examples. A quick example spikesorting graph to show the spikeinterface team

ExData_Plotting1. Plotting Assignment 1 for Exploratory Data Analysis

LeabraExample.

nvidia-patch. This patch removes restriction on maximum number of simultaneous NVENC video encoding sessions imposed by Nvidia to consumer-grade GPUs.

repulsive-autoencoder. Variations on the Variational Autoencoder

multicam-calibration. Multi-camera calibration (intrinsics, extrinsics, and bundle adjustment)

d3-plugins. A repository for sharing D3.js plugins.

example_r_colab_project. Just a tiny example project for running your R code on colab