🚀 By Science and FOR SCIENCE 🇫🇷

PhysiQuanty PRO

PhysiQuanty

·

PhysiQuanty

AI & ML interests

Theoretical Physics 🇫🇷 The perceptron is not a neuron ; ElectroChemical Calculations (NMDA & AMPA receptor, apical and basal dendrite, axon initial segment)

Recent Activity

liked a dataset about 4 hours ago

Bayway/italian-open-timeseries

reacted to Bayway's post with 🧠 about 4 hours ago

Italian Open Time Series: 46 public Italian series for zero-shot forecasting, and a first live test of Timestral Italian data is almost absent from the corpora that time-series foundation models are trained and benchmarked on. So I collected 46 open series (CC0/CC BY): smog in Milan, bikes in Bologna, tourism, energy, earthquakes, deaths, Italian Wikipedia. Gaps stay NaN, and a tasks.yaml makes every window reproducible with fev. Seven models, zero-shot, 19 tasks (Timestral 5M to 209M, Chronos-2, TimesFM 3.0, Toto 2.0). Skill vs seasonal naive, fev-bench style: • Backtest, windows ending 14 Oct, Timestral's release day: Toto 2.0 28.4, Timestral-209M 28.2 • Live, data published after that day (6 tasks, ~1 week): Timestral-209M 32.2, Timestral-123M 30.9, TimesFM 3.0 30.3, Toto 2.0 27.7 • Monthly consumer prices of electricity and gas: plain AutoETS beats every foundation model The live round is small; I'll re-run it every week. Two surprises. Weather beats the calendar. On a Bologna bike counter, giving Timestral the observed weather of the forecast days (a perfect forecast) cut the error by 17%. Holidays and bridge days alone: 4%. Daylight saving time. The model works in UTC; cyclists don't. Across the 25 Oct clock change my first version put Monday's rush hour at 5 am, until I moved the series to Italian wall-clock time. For Bologna there's a small page: pick a street and a day in the next week for an hourly bike forecast, computed live from the city's counts and Open-Meteo, plus a map of counters and air-quality stations. Dataset: https://huggingface.co/datasets/Bayway/italian-open-timeseries Bologna: https://huggingface.co/spaces/Bayway/due-torri-due-ruote Not included: GME wholesale power prices and Terna load data. Their terms forbid redistribution, and GME bans automated extraction for any purpose, AI training included.

liked a dataset about 16 hours ago

taohan10200/CRA5-Dataset

View all activity

Organizations

PhysiQuanty 's models 13

PhysiQuanty/Self-Predicting-Gradient-Descent

PhysiQuanty/Binary-LLM-POC

Text Generation • 10.7M • Updated May 2 • 576 • 12

PhysiQuanty/Wiki-Test2

79.7M • Updated Mar 4 • 8

PhysiQuanty/Wiki-Test

79.7M • Updated Mar 3 • 10 • 1

PhysiQuanty/Patenty-Test2-Radix-65536

79.7M • Updated Mar 2 • 11

PhysiQuanty/VOCAB-4294967296-FOUR-LOGITS-256

13.7M • Updated Feb 25 • 17 • 2

PhysiQuanty/Patent-Dual-Cross-Entropie

46.5M • Updated Feb 24 • 3

PhysiQuanty/Patent-Test-Radix-65536-AutoTokenizer_FineTune

79.7M • Updated Feb 23 • 18

PhysiQuanty/Patenty-0.1

79.7M • Updated Feb 22 • 6

PhysiQuanty/Patenty1-0.1B

79.7M • Updated Feb 19 • 7

PhysiQuanty/Patent-Test-Radix-65536-AutoTokenizer

79.7M • Updated Feb 13 • 5

PhysiQuanty/Patent-Test-Radix-65536

79.7M • Updated Feb 12 • 8

PhysiQuanty/Binary-Addition-LLM-POC

Text Generation • 10.7M • Updated Feb 5 • 19 • 4