Humans vs. Animals: The Value Debate

AI Found Particle Tracks Physicists Didn't Expect (ft. Daniel Whiteson)

The Thought Process of a Data Scientist 👩‍💻 I didn’t start by picking a neural network - I started by understanding the data and the problem it represents. Because fraud is rare, every design choice had to focus on stability, generalization, and meaningful evaluation instead of flashy complexity. The network is intentionally simple, not because it’s weak, but because simple models reveal whether the signal is real. In the end, the model doesn’t make decisions for us - it produces probabilities