• 学习时长

    8周/建议每周至少6小时

  • 答疑服务

    专属微信答疑群/讲师助教均参与

  • 作业批改

    每章节设计作业/助教及时批改评优

  • 第2章: Evaluation Approaches and Metrics for Recommender Systems
  • 任务4: 【课件】推荐系统 Lecture2.pdf
  • 第1节: Introduction
  • 任务5: 【视频】Introduction
  • 第2节: Evaluation approaches for recommender systems(Offline experiments,User studies,Online trails)
  • 任务6: 【视频】Evaluation approaches 21:06
  • 第3节: Evaluation metrics of recommender systems(Accuracy metrics,Non-accuracy metrics)
  • 任务7: 【视频】Evaluation metrics
  • 第4节: Summary and thinking
  • 任务8-1: 【视频】Summary and thinking
  • 任务8-2: 【作业】第2次
  • 第4章: Factorization Approaches in Recommender Systems
  • 第1节: The $1 Million Netflix Challenge
  • 第2节: Matrix factorization for rating prediction
  • 第3节: Feature-based matrix factorization
  • 第4节: Learning high-order interaction with tensor factorization models
  • 第5节: A unified factorization framework: factorization machines (FM)
  • 第6节: Practice I:Implement ALS MF
  • 第7节: Practice II:Implement feature based MF
  • 第5章: Bridge Deep Learning to Recommender Systems
  • 第1节: Preliminary of artificial neural networks
  • 第2节: A brief review of deep learning
  • 第3节: Using deep learning models for recommendation
  • 第4节: Practice l:Implement Deep Regression Model to predict movie ratings
  • 第5节: Practice II:Implement Neural MF to predict movie ratings
  • 第6章: Session-based Recommender Systems
  • 第1节: Modelling users' session or sequential behaviours for recommendations
  • 第2节: Learning users' dynamic preferences from session data
  • 第3节: Session-based recommender systems based on Markov chain models
  • 第4节: Session-based recommender systems based on recurrent neural networks (RNN)
  • 第5节: Practice I:Implement a Markov chain based next-basket recommender systems
  • 第6节: Practice II:Implement an RNN-based SBRS GRU4REC
  • 第7章: Graph-based Recommender Systems
  • 第1节: Graphs in recommender systems
  • 第2节: Recommendation with random walks
  • 第3节: Graph kernels for ranking
  • 第4节: Graph neural networks (GNN) for multiple relation based recommendation
  • 第5节: Practice I:Implement a random walk-based recommender system for friend recommendation in a social network dataset.
  • 第6节: Practice II:Implement a GNN-based recommender system for social recommendation to incorporate social relations for rating prediction.
  • 第8章: Towards Semantic and Explainable Recommender Systems
  • 第1节: Did Donald Trump use AI to win the election?
  • 第2节: Preliminary for natural language processing
  • 第3节: Sentiment analysis in recommender systems
  • 第4节: Preliminary for knowledge representation
  • 第5节: Building semantic recommender systems over knowledge graphs
  • 第6节: Assignments

相关推荐

自然语言处理 知识图谱 进阶