Callum Bruce

@astro_reid @Astro_Christina @astro_reid, @Astro_Christina this is awesome! Q: in each image returned of the flyby, the Moon looks slightly different (camera exposure settings/phase of the flyby? i.e. art002e010208 vs art002e009289). Which image(s) standout as being closest to what the human eye sees?

Only one chance in this lifetime… Like watching sunset at the beach from the most foreign seat in the cosmos, I couldn’t resist a cell phone video of Earthset. You can hear the shutter on the Nikon as @Astro_Christina is hammering away on 3-shot brackets and capturing those exceptional Earthset photos through the 400mm lens. @AstroVicGlover was in window 3 watching with @Astro_Jeremy next to him. I could barely see the Moon through the docking hatch window but the iPhone was the perfect size to catch the view…this is uncropped, uncut with 8x zoom which is quite comparable to the view of the human eye. Enjoy.

@NASA @NASA - incredible! We've already started passing these images through our Crater Detection Algorithm. Can you put me in contact with the OpNav team to discuss our autonomous OpNav tech?

Hello, Moon. It’s great to be back. Here’s a taste of what the Artemis II astronauts photographed during their flight around the Moon. Check out more photos from the mission: nasa.gov/artemis-ii-mul…

Tycho Orbital is developing autonomous optical navigation technologies for lunar missions. Using craters detected in images, we can determine the spacecraft's position fully autonomously. linkedin.com/company/tycho-…

Following the lunar flyby, the Artemis II mission started returning some incredible photos of the lunar far side. We couldn't resist running them through our crater instance segmentation model - a core part of our Crater Detection Algorithm (CDA). @NASA @NASAArtemis @NASAAdmin

@chr1sa I used "long tail" to describe the elapsed time distribution in a population of position estimates from our OpNav algorithm when presenting to a university group last week and thought of you @chr1sa 👍🏻

Interestingly, the term "long tail" is more popular now than it was when I coined it in an Internet context in Wired nearly twenty years ago. Then it was largely an economic concept, about the Internet's ability to surface latent demand for goods and services not found in bricks-and-mortar stores. Now it mostly just refers to near-infinite variety of any sort in systems with classic powerlaw distribution, from weird edge-case scenarios that self-driving cars have to deal with to the explosion of bespoke vibecoded apps.

Callum Bruce @callumbruce91 demystifies transformer architecture by guiding readers step by step through the construction and training of a time-series denoising model using TensorFlow. The model performs well and can be used for specialized tasks. ai.gopubby.com/fa7dbdf895a3

Mechazilla has caught the Super Heavy booster!

I posted "How to Program a Neural Network" on Medium a little over a year ago. With over 36k views and 10k reads it has reached far more people than I imagined possible. I've added a free-to-view link at the top of the article so anyone can now access it medium.com/towards-data-s…

"In this article, we will develop a crater detection algorithm (CDA) for an autonomous crater-based optical navigation system for spacecraft in orbit of the Moon." Lunar Crater Detection: Computer Vision in Space by @callumbruce91 buff.ly/4bm1UmH

#MachineLearning #ComputerVision #ImageSegmentation #Space #TheMoon

Crater detection algorithms (CDA) are a crucial part of future autonomous crater-based navigation systems onboard spacecraft. Follow the implementation of a CDA based on the #segmentanythingmodel in my latest Medium article published in @TDataScience: towardsdatascience.com/lunar-crater-d…

Delighted to share that I successfully defended my PhD on Urban #bluespace and #health using #systemsthinking 💙 Next project? Being a ma!🤰 #PhDandPregnant #PhDone @GCUSHLS

⚫⚪♥️

A step-by-step guide to implementing a neural network from scratch by @callumbruce91 buff.ly/3RxO3Dh

Have you ever wondered how a neural network works? Follow along as I explain, step-by-step, how to implement a neural network from scratch in "How to Program a Neural Network", published in @TDataScience. #NeuralNetworks #MachineLearning #deeplearning towardsdatascience.com/how-to-program…

... ... and here is how the Chandrayaan-3 Rover ramped down from the Lander to the Lunar surface.

Dive deep into one of the fundamental methods deployed in machine learning—the gradient descent algorithm—and follow along as @callumbruce91 explains how you can use it to solve engineering optimization problems. buff.ly/44OI14G

What if you use #machinelearning to solve engineering optimization problems? 🤔 Read about this in my latest article, published in @TDataScience PID Controller Optimization: A Gradient Descent Approach towardsdatascience.com/pid-controller…