J'ai profité de l'IA pour porter mon assistant de déduction naturelle en une page web marcdefalco.github.io/dedunat/
Le moteur d'inférence, lui, est toujours entièrement humain !
marcdefalco.github.io
Dedunat
Marc de Falco
@marcdefalco.eurosky.social
443 followers 120 following 214 posts
IGÉSR, responsable du pôle Données, IA et Numérique, groupes mathématiques et informatique
![Comic. A snake slithers around a hypercube. No two non-consecutive parts of its coils can be on adjacent corners. [Three small 4-dimensional hypercubes showing disallowed options with one large cube with snake wrapped around it. Dimensions = 4. Max Length - 7.] Snake(N) = Longest snake that can fit in an n-dimensional hypercube. Snake(N=1, 2, 3…8) = 1, 2, 4, 7, 13, 26, 50, 98. Snake(N>8) = UNSOLVED. [caption] It turns out every scientific field has a key thought experiment that involves putting a cute animal in a weird box for no reason. So far, quantum mechanics and graph theory have found theirs, but most other fields are still working on it.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreicjbjwxfe3ef6styvrvsjtt63znh24tfuqxlceewi3b6t7zfu756i)
![Exemple de tri avec le programme Python à côté.
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_distances
import numpy as np
import random
import sys
model = SentenceTransformer(
'intfloat/multilingual-e5-large-instruct')
def compute_embeds(sentences):
return model.encode(sentences, batch_size=256)
def semantic_sort(texts):
sorted_texts = []
embeds = compute_embeds(texts)
n = len(texts)
distance_matrix = cosine_distances(embeds)
visited = set()
x = random.randrange(0, n)
for _ in range(n):
sorted_texts.append(texts[x])
visited.add(x)
neighbours = [
distance_matrix[x][y]
if y not in visited else np.inf for y in range(n)]
x = np.argmin(neighbours)
return sorted_texts](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:5b4c5adbwuda3puzht2lhmiu/bafkreiebdmhapaio37d5datmjhidwc7vrvjywrxsbgjiqsnsdzvd5crtwu)
