Fast computation of a coranking matrix for dimensionality reduction with python, joblib, and numba
Posted on Mon 19 July 2021 in dimensionality reduction • Tagged with umap, coranking matrix, metrics
Parametric UMAP
Posted on Sat 03 October 2020 in Machine Learning • Tagged with UMAP, Parametric UMAP, Dimensionality Reduction
Our new paper, "Parametric UMAP: learning embeddings with deep neural networks for representation and semi-supervised learning" is on arXiv.
Continue reading
Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 4: DeepDream and style transfer
Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields
A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at filtering images using different layers of a deep neural network. We also perform style transfer, by modifying an image to have similar layer activations as a second source image.
Continue reading
Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 3: Reconstructing images from layer activations
Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields
A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at how much information is contained about the original image by trying to reconstruct the image based upon layer activations.
Continue reading
Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 2: Visualizing features and receptive fields
Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields
A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at visualizing classes.
Continue reading
Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 1: Visualizing classes
Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields
A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at visualizing classes.
Continue reading
Plotting my research notes with NetworkX and sigma.js
Posted on Sat 21 September 2019 in data science • Tagged with research notes, sigma.js, network science, plotting, data science, wordpress, xml, rss
OpenEphys on the Raspberry Pi 4
Posted on Sat 21 September 2019 in neuroscience • Tagged with raspberry pi, open ephys, neuroscience, neural recordings, open science
Parallels in the sequential organization of birdsong and human speech
Posted on Sat 17 August 2019 in Birdsong • Tagged with birdsong, language, speech, finch, starling, vireo, thrasher, syntax, phonology
We released a new paper about the sequential organization of speech and birdsong in Nature Communications. Our paper models sequential mutual information of both signals, and shows similarities in the long- and short-range organization between birdsong and speech.
Continue reading
Making an HTML CV in Python using Jinja
Posted on Fri 07 June 2019 in python • Tagged with python, cv, curriculum vitae, jinja, html, css, json
Making Jupyter notebooks Google Colab ready
Posted on Fri 07 June 2019 in python • Tagged with jupyter, python, google colab
An example of how to run Jupyter notebooks on Google Colab even when they require additional dependencies.
Continue reading
Libtfr Time Frequency Reassigned Spectrogram example
Posted on Thu 23 May 2019 in Signal Processing • Tagged with spectrograms, python, jupyter
Converting from HDF5 to tfrecord and reading tfrecords into tensorflow
Posted on Mon 29 April 2019 in Tensorflow • Tagged with tensorflow hdf5, tfrecord, convert
CCN 2018 Conference presentation: Learned context dependent categorical perception in a songbird
Posted on Tue 19 March 2019 in birdsong • Tagged with birdsong, machine learning, variational autoencoder, context, category learning
My conference poster and oral presentation from CCN 2018 on the context dependent categorical perception behavior I designed for songbirds
Continue reading
Songbird Data Science Workshop 2018: AVGN video
Posted on Tue 19 March 2019 in birdsong • Tagged with birdsong, machine learning, variational autoencoder, UMAP, GAIA, GAN, unsupervised learning
birdbrain: a library for viewing songbird (and bat) brain atlases
Posted on Fri 15 March 2019 in Birdsong • Tagged with MRI, atlas, songbird, canary, zebra finch, mustached bat, european starling, pigeon, brain, python
A python package for use with the songbird brain atlases focusing on stereotactic localization of the European starling, Canary, Zebra finch, Pigeon, and Mustached bat.
Continue reading
Live behavioral updates on Gentnerlab Website
Posted on Mon 11 February 2019 in Birdsong • Tagged with pyoperant, RPiOperant, operant conditioning, behavior
Generative Adversarial Interpolative Autoencoding (GAIA)
Posted on Sun 07 October 2018 in Machine Learning • Tagged with tensorflow, gan, adversarial, convex, autoencoder, GAIA
A novel interpolation-based Generative Adversarial Network / Autoencoder written in Tensorflow
Continue reading
Noise reduction using spectral gating in python
Posted on Sat 07 July 2018 in Signal Processing • Tagged with spectrograms, python, jupyter
A quick implementation of a noise reduction algorithm using spectral gating in python.
Continue reading
Spectrograms, MFCCs, and Inversion in Python
Posted on Sat 07 July 2018 in Signal Processing • Tagged with griffin-lim, spectrogram, inversion, python, audio
Variational Autoencoder in Tensorflow (Jupyter Notebook)
Posted on Sat 07 July 2018 in Machine Learning • Tagged with tensorflow, vae, variational autoencoder, python, autoencoder