计算机与人工智能：XX学习XX学习XX学习

尝试随手开一个新板块，记录整理自己之前部分容易弄混淆的概念。英文写了润色再翻译成中文。

计算机科学与人工智能的区别和联系。

让我们深入探讨一些线上媒体中不太容易区分的概念。

这些核心技术领域包括：计算机科学(CS)、人工智能(AI)、机器学习(ML)、深度学习(DL)、强化学习(RL)和人工神经网络(ANNs)。

计算机科学(CS)是一个全面的领域，专注于计算机的理论基础及其实际应用，包括算法和数据结构、操作系统、计算机网络、计算机架构、人工智能、数据库以及相关学科。

人工智能(AI)目前缺乏普遍认可的定义，在学术学科和行业应用中有不同的解释。从我的角度来看，AI是使机器能够模拟类人智能行为的技术和系统。人工智能和计算机科学是深度交叉的学科。

机器学习(ML)是人工智能(AI)的一个子领域：根据Tom Mitchell的定义，"如果一个计算机程序在经验E的基础上，对于某类任务T和性能度量P，随着经验E的增加而提高其在T上的性能（按P衡量），那么就说这个程序从经验中学习。"

深度学习(DL)，作为机器学习(ML)的一个子领域，使用深度神经网络(DNNs)——具有多个隐藏层的人工神经架构——通过连续的抽象层次学习层次化数据表示，模仿类似于生物认知的统计模式识别能力。

强化学习(RL)，机器学习(ML)的一个子领域，涉及自动智能体通过与动态环境的迭代交互来发展决策策略。这些代理通过奖励信号(积极强化)或惩罚(负面反馈)来优化其行为，与形式化的马尔可夫决策过程(MDPs)相一致。

人工神经网络(ANNs)是一种受人脑结构和功能启发的计算模型。它是一种机器学习算法，使用相互连接的节点（称为神经元）来处理信息和进行预测。人工神经网络是深度学习的基础。

English practice

What is the difference and relationship between the CS and AI.

Let's take a deeper look at some of the less distinguishable concepts in online media.

These core technical domains encompass: computer science, artificial intelligence (AI), machine learning (ML), deep learning, reinforcement learning, and artificial neural networks (ANNs)

Computer Science(CS) is a comprehensive field focused on both theoretical foundations, and their practical applications, encompassing algorithms and data structure, operating system, computer network, computer architecture, artificial intelligence, database and related disciplines.

Artificial Intelligence(AI) currently lacks a universally agreed-upon definition, with interpretations varying across academic disciplines and industry applications. From my perspective, AI is the technologies and systems that enable machines to simulate the human-like intelligent behaviors. Artificial intelligence and computer science are deeply intertwined disciplines.

Machine learning(ML) is a subfield of artificial intelligence: according to Tom Mitchell” A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”

Deep Learning (DL), a subfield of machine learning (ML), employs deep neural networks (DNNs)—artificial neural architectures with multiple hidden layers—to learn hierarchical data representations through successive layers of abstraction, mimicking statistical pattern recognition capabilities akin to biological cognition.

Reinforcement Learning (RL), a subfield of machine learning (ML), involves autonomous agents developing decision-making policies through iterative interactions with dynamic environments. These agents optimize their behavior via reward signals (positive reinforcements) or penalties (negative feedback), aligning with formalized Markov decision processes (MDPs)

Artificial Neural Network is a computational model inspired by the structure and function of the human brain. It's a type of machine learning algorithm that uses interconnected nodes, called neurons, to process information and make predictions. Artificial neural networks are the foundation of deep learning.

分享

收藏

点赞

在看