Two Years in the Tenure Track
Published:
Reflecting on my journey towards becoming a tenure-track astronomer
Posts by Tags
academia
advice
Two Years in the Tenure Track
Published:
Reflecting on my journey towards becoming a tenure-track astronomer
blogging
Lowering the barrier to writing more frequently
Published:
Writing these posts is fun but time-consuming. How can I stay motivated enough to post consistently? To sustain a habit of writing, I’ll need to create an easier path for my future self.
Hello World (again)!
Published:
Oh hey, it’s me again. Yes, I’m going to try to write more blog posts. Yes, I’ve promised that before. Sorry. This time it’ll be different.
computer-vision
Astronomical Super-resolution, Part II: GANs
Published:
Generative adversarial networks are magical… when they work.
Astronomical Super-resolution, Part I: U-Nets
Published:
Training a U-Net to enhance images of galaxies.
What do galaxies look like? Learning from variational autoencoders
Published:
Exploring the latent space of galaxy images with autoencoders.
Visualizing deep learning with galaxies, part 1
Published:
Let’s explore the morphological feature space of galaxies represented by a trained CNN. We will use PCA to reduce the dimensionality of the neural network’s latent features, and then visualize these features with matplotlib.
Training a deep CNN to learn about galaxies in 15 minutes
Published:
Let’s train a deep neural network from scratch! In this post, I provide a demonstration of how to optimize a model in order to predict galaxy metallicities using images, and I discuss some tricks for speeding up training and obtaining better results.
Deep learning with galaxy images
Published:
Welcome! In this first post to my blog, we will take a deeper look at galaxy images. Why should we bother measuring the metallicities, or elemental abundances, of other galaxies? And why would we use convolutional neural networks? Read more to find out!
data-science
Identifying racial bias in health data
Published:
We are becoming more and more reliant on machine learning algorithms in our everyday lives. But what if these algorithms aren’t fair? In this exploratory data analysis of Obermeyer et al. 2019, we look at how racial biases can creep in to an algorithm’s decision-making process.
galaxies
Astronomical Super-resolution, Part II: GANs
Published:
Generative adversarial networks are magical… when they work.
Astronomical Super-resolution, Part I: U-Nets
Published:
Training a U-Net to enhance images of galaxies.
What do galaxies look like? Learning from variational autoencoders
Published:
Exploring the latent space of galaxy images with autoencoders.
Visualizing deep learning with galaxies, part 2
Published:
In the previous post, we examined the feature space of galaxy morphological features. Now, we will use the Grad-CAM algorithm to visualize the parts of a galaxy image that are most strongly associated with certain classifications. This will allows us to identify exactly which morphological features are correlated with low- and high-metallicity predictions.
Visualizing deep learning with galaxies, part 1
Published:
Let’s explore the morphological feature space of galaxies represented by a trained CNN. We will use PCA to reduce the dimensionality of the neural network’s latent features, and then visualize these features with matplotlib.
Training a deep CNN to learn about galaxies in 15 minutes
Published:
Let’s train a deep neural network from scratch! In this post, I provide a demonstration of how to optimize a model in order to predict galaxy metallicities using images, and I discuss some tricks for speeding up training and obtaining better results.
Deep learning with galaxy images
Published:
Welcome! In this first post to my blog, we will take a deeper look at galaxy images. Why should we bother measuring the metallicities, or elemental abundances, of other galaxies? And why would we use convolutional neural networks? Read more to find out!
llms
Lowering the barrier to writing more frequently
Published:
Writing these posts is fun but time-consuming. How can I stay motivated enough to post consistently? To sustain a habit of writing, I’ll need to create an easier path for my future self.
original-blog
Visualizing deep learning with galaxies, part 2
Published:
In the previous post, we examined the feature space of galaxy morphological features. Now, we will use the Grad-CAM algorithm to visualize the parts of a galaxy image that are most strongly associated with certain classifications. This will allows us to identify exactly which morphological features are correlated with low- and high-metallicity predictions.
Visualizing deep learning with galaxies, part 1
Published:
Let’s explore the morphological feature space of galaxies represented by a trained CNN. We will use PCA to reduce the dimensionality of the neural network’s latent features, and then visualize these features with matplotlib.
Identifying racial bias in health data
Published:
We are becoming more and more reliant on machine learning algorithms in our everyday lives. But what if these algorithms aren’t fair? In this exploratory data analysis of Obermeyer et al. 2019, we look at how racial biases can creep in to an algorithm’s decision-making process.
Training a deep CNN to learn about galaxies in 15 minutes
Published:
Let’s train a deep neural network from scratch! In this post, I provide a demonstration of how to optimize a model in order to predict galaxy metallicities using images, and I discuss some tricks for speeding up training and obtaining better results.
Deep learning with galaxy images
Published:
Welcome! In this first post to my blog, we will take a deeper look at galaxy images. Why should we bother measuring the metallicities, or elemental abundances, of other galaxies? And why would we use convolutional neural networks? Read more to find out!
personal
Hello World (again)!
Published:
Oh hey, it’s me again. Yes, I’m going to try to write more blog posts. Yes, I’ve promised that before. Sorry. This time it’ll be different.
Two Years in the Tenure Track
Published:
Reflecting on my journey towards becoming a tenure-track astronomer
productivity
Lowering the barrier to writing more frequently
Published:
Writing these posts is fun but time-consuming. How can I stay motivated enough to post consistently? To sustain a habit of writing, I’ll need to create an easier path for my future self.
substack-blog
Two Years in the Tenure Track
Published:
Reflecting on my journey towards becoming a tenure-track astronomer
Astronomical Super-resolution, Part II: GANs
Published:
Generative adversarial networks are magical… when they work.
Astronomical Super-resolution, Part I: U-Nets
Published:
Training a U-Net to enhance images of galaxies.
What do galaxies look like? Learning from variational autoencoders
Published:
Exploring the latent space of galaxy images with autoencoders.
tutorial
Astronomical Super-resolution, Part II: GANs
Published:
Generative adversarial networks are magical… when they work.
Astronomical Super-resolution, Part I: U-Nets
Published:
Training a U-Net to enhance images of galaxies.
What do galaxies look like? Learning from variational autoencoders
Published:
Exploring the latent space of galaxy images with autoencoders.
Visualizing deep learning with galaxies, part 2
Published:
In the previous post, we examined the feature space of galaxy morphological features. Now, we will use the Grad-CAM algorithm to visualize the parts of a galaxy image that are most strongly associated with certain classifications. This will allows us to identify exactly which morphological features are correlated with low- and high-metallicity predictions.
Visualizing deep learning with galaxies, part 1
Published:
Let’s explore the morphological feature space of galaxies represented by a trained CNN. We will use PCA to reduce the dimensionality of the neural network’s latent features, and then visualize these features with matplotlib.
Identifying racial bias in health data
Published:
We are becoming more and more reliant on machine learning algorithms in our everyday lives. But what if these algorithms aren’t fair? In this exploratory data analysis of Obermeyer et al. 2019, we look at how racial biases can creep in to an algorithm’s decision-making process.
Training a deep CNN to learn about galaxies in 15 minutes
Published:
Let’s train a deep neural network from scratch! In this post, I provide a demonstration of how to optimize a model in order to predict galaxy metallicities using images, and I discuss some tricks for speeding up training and obtaining better results.
visualization
Visualizing deep learning with galaxies, part 2
Published:
In the previous post, we examined the feature space of galaxy morphological features. Now, we will use the Grad-CAM algorithm to visualize the parts of a galaxy image that are most strongly associated with certain classifications. This will allows us to identify exactly which morphological features are correlated with low- and high-metallicity predictions.
Visualizing deep learning with galaxies, part 1
Published:
Let’s explore the morphological feature space of galaxies represented by a trained CNN. We will use PCA to reduce the dimensionality of the neural network’s latent features, and then visualize these features with matplotlib.