Freezing

Freezing

Freeeeeezing......
twitter
github
cover

Some thoughts on Bayesian formula

Under the assumptions of the total probability formula, we get the celebrated Bayes’ formula, a famous theorem in probability theory. This…
cover
cover
cover
cover
cover
cover
cover
cover
cover
cover

Stanford CS231n(2017版)-- Lecture 3:Loss Function and Optimization

在否决了 Lecture 2 中的 Nearest Neighbor 之后,接下来要尝试的是 Linear Classification。 Introduction 我们采用参数化的方法来做分类 如上图所示,用一个 103072 的参数矩阵 W,乘上 x (x…
cover
cover
cover
cover
cover
cover
cover
cover
cover
cover

Stanford CS231n(2017版)-- Lecture 2 笔记

Lecture 2 主要讲的是 image classification 的一些基础知识 (核心概念会用英语原味表达) 从最经典的例子入手:给你一张猫的图片,如何从一堆标签中正确地 pick 猫这个标签呢? 一言以蔽之,需要解决的是: Semantic gap between…
cover

具身智能

具身智能的浪潮与前沿思考 一、 核心概念:重新理解 “老” 概念与智能的演化 1. 什么是具身智能? 具身智能并非一个全新的概念,其根源可追溯至上世纪六七十年代的 “具身假说”(Embodied Hypothesis)。其核心思想是:智能并非孤立存在于计算之中…
cover

Why We Think?

本文是 Lilian Weng 最近写的一篇博客,对她的许多观点表示赞同,也受到了很多启发。 原文链接:https://lilianweng.github.io/posts/2025-05-01-thinking/ 赋予动机 与心理学的类比 计算即资源 潜在变量建模 基…
Ownership of this blog data is guaranteed by blockchain and smart contracts to the creator alone.