James Ashford
Researcher in Machine Learning and Genetics. Here to explore projects in ALife and machine learning - particularly interested in self organising systems and interpretability! (he/him)
- Reposted by James Ashford
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordThere's not a single crime in the history of the UK that would have been prevented by a bathroom bill. Not one Bathroom bills aren't about safety, they're about trying to exclude LGBT people from public life. That's it
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordAs a former child junior olympic-level runner, I have a few thoughts on the attacks on trans girls in sports. I ran for one of the most competitive teams in Southern California, and people who ran for my have gone on to become professional athletes. And these bans: they're fucking NONSENSE. 🧵
- Reposted by James AshfordWe released our preprint on the CREsted package. CREsted allows for complete modeling of cell type-specific enhancer codes from scATAC-seq data. We demonstrate CREsted’s robust functionality in various species and tissues, and in vivo validate our findings: www.biorxiv.org/content/10.1...
- Reposted by James AshfordVery proud of two new preprints from the lab: 1) CREsted: to train sequence-to-function deep learning models on scATAC-seq atlases, and use them to decipher enhancer logic and design synthetic enhancers. This has been a wonderful lab-wide collaborative effort. www.biorxiv.org/content/10.1...
- Reposted by James AshfordPrinter post 2025 is here lol www.theverge.com/tech/641940/...
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordImagine that the five most overconfident boys at your local high school, who learned how to use a hammer last semester, are planning to tear down your entire city and rebuild it from scratch using guidance from a Speak and Spell
- Reposted by James Ashford1. Today the Tories unveil their new policy: ripping up the commitment to net zero by 2050. Kemi Badenoch, with no evidence, claims "it can’t be achieved without a serious drop in our living standards or by bankrupting us." What the evidence shows is the opposite. We can't prosper without it. 🧵
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashfordits amazing how chatgpt knows everything about subjects I know nothing about, but is wrong like 40% of the time in things im an expert on. not going to think about this any further
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordIt may not be cool or hip in some circles, but we legitimately do need a massive amount of people to run for office. Flood the school boards, councils, county seats, state legislatures, Congress, etc. Big changes at the top happen when the ground shifts at the bottom. And that can start now.
- Reposted by James Ashford
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordAbstract map. #genuary #genuary30
- Reposted by James Ashford[Not loaded yet]
- #genuary2025 #genuary31 #genuary Pixel Sorting. A gentle finish to the month (only a bit late!) remixing my day 2 art. Love how concise this is with numpy. Code here: github.com/JELAshford/g...
- Reposted by James Ashford[Not loaded yet]
- #genuary2025 #genuary30 #genuary Abstract map! Another experiment with Perlin noise and thresholds. Code here: github.com/JELAshford/g...
- Reposted by James AshfordAny countries whose scientific research funding bodies are NOT currently under siege by their own national leadership would do very well announcing investments in bringing in foreign research talent right now
- #genuary2025 #genuary29 #genuary Grid-based graphics! Lots of rectangles, with random rotations applied to squares arranged in a grid. Sort of forest-y! Code here: github.com/JELAshford/g...
- #genuary2025 #genuary28 #genuary Infinite scroll! I'm back from the house move, I can finally finsh these off. Here's some infinitely looping random walks - that always come back to the same spot! Code here: github.com/JELAshford/g...
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- #genuary2025 #genuary27 #genuary Interesting with no randomness or trig. Like others, this prompt screamed elementary cellular automata to me! I used a window of 5 instead of 3 (4.3 billion rule combinations instead of 256!) and searched for a cool pattern. Code here: github.com/JELAshford/g...
- #genuary2025 #genuary26 #genuary Symmetry! Behold the bestiary! Each formed from 6 random reflections of a starting central circle - shockingly simple once I learned about point projection. Highly recommend running the code with different seeds: github.com/JELAshford/g...
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- #genuary2025 #genuary25 #genuary A line that may or may not intersect. Applied the Chaos Game to the sequence of a random gene from the human genome - this one is "P51532". Code here: github.com/JELAshford/g...
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James Ashford[Not loaded yet]
- Reposted by James AshfordI wanted to write briefly about a very pleasant experience we recently had coordinating and collaborating closely on competing publications with 2 other teams. 1/
- Reposted by James Ashford[Not loaded yet]
