机器学习

机器学习课程介绍如何创建使用和分析大规模数据的系统。具体内容包括预测算法、自然语言处理以及统计模式识别。

...
Deep Learning
deeplearning.ai
Deep Learning
专项课程
IBM AI Foundations for Business
IBM
IBM AI Foundations for Business
专项课程
Applied Data Science
IBM
Applied Data Science
专项课程
Natural Language Processing
deeplearning.ai
Natural Language Processing
专项课程
Data Science: Foundations using R
Johns Hopkins University
Data Science: Foundations using R
专项课程
TensorFlow in Practice
deeplearning.ai
TensorFlow in Practice
专项课程
Data Engineering, Big Data, and Machine Learning on GCP
Google Cloud
Data Engineering, Big Data, and Machine Learning on GCP
专项课程
Mathematics for Machine Learning
Imperial College London
Mathematics for Machine Learning
专项课程
Reinforcement Learning
University of Alberta
Reinforcement Learning
专项课程
AI for Medicine
deeplearning.ai
AI for Medicine
专项课程
Advanced Machine Learning
National Research University Higher School of Economics
Advanced Machine Learning
专项课程
Advanced Data Science with IBM
IBM
Advanced Data Science with IBM
专项课程
Data Science: Statistics and Machine Learning
Johns Hopkins University
Data Science: Statistics and Machine Learning
专项课程
Machine Learning with TensorFlow on Google Cloud Platform
Google Cloud
Machine Learning with TensorFlow on Google Cloud Platform
专项课程
Big Data
University of California San Diego
Big Data
专项课程
Investment Management with Python and Machine Learning
EDHEC Business School
Investment Management with Python and Machine Learning
专项课程
Машинное обучение и анализ данных
Moscow Institute of Physics and Technology
Машинное обучение и анализ данных
专项课程
Machine Learning
University of Washington
Machine Learning
专项课程
Robotics
University of Pennsylvania
Robotics
专项课程

    关于 机器学习 的常见问题

  • Machine learning is a branch of artificial intelligence that seeks to build computer systems that can learn from data without human intervention. These powerful techniques rely on the creation of sophisticated analytical models that are “trained” to recognize patterns within a specific dataset before being unleashed to apply these patterns to more and more data, steadily improving performance without further guidance.

    For example, machine learning is making increasingly accurate image recognition algorithms possible. Human programmers provide a relatively small set of images that are labeled as “cars” or “not cars,” for instance, and then expose the algorithms to vastly larger numbers of images to learn from. While the iterative algorithms typically used in machine learning aren’t new, the power of today’s computing systems have enabled this method of data analysis to become more effective more rapidly than ever.