李宏毅:机器学习的下一步
共61课时 12小时45分47秒秒
简介
李宏毅老师2019年最新机器学习视频教程
李宏毅老师于2012年从台湾大学博士毕业。并于2013年赴麻省理工学院(MIT)计算机科学和人工智能实验室做访问学者。现任台湾大学电机系副教授。主要研究领域为机器学习(特别是深度学习)、口语语义理解和语音识别。李老师的个人主页是:http://speech.ee.ntu.edu.tw/~tlkagk
章节
- 课时1:The Next Step for Machine Learning (15分26秒)
- 课时2:Anomaly Detection (1) (13分22秒)
- 课时3:Anomaly Detection (2) (14分9秒)
- 课时4:Anomaly Detection (3) (14分4秒)
- 课时5:Anomaly Detection (4) (4分6秒)
- 课时6:Anomaly Detection (5) (12分17秒)
- 课时7:Anomaly Detection (6) (12分18秒)
- 课时8:Anomaly Detection (7) (6分1秒)
- 课时9:Attack ML Models (1) (6分5秒)
- 课时10:Attack ML Models (2) (11分41秒)
- 课时11:Attack ML Models (3) (7分2秒)
- 课时12:Attack ML Models (4) (8分11秒)
- 课时13:Attack ML Models (5) (6分37秒)
- 课时14:Attack ML Models (6) (9分25秒)
- 课时15:Attack ML Models (7) (8分2秒)
- 课时16:Attack ML Models (8) (10分10秒)
- 课时17:Explainable ML (1) (13分50秒)
- 课时18:Explainable ML (2) (14分7秒)
- 课时19:Explainable ML (3) (6分6秒)
- 课时20:Explainable ML (4) (7分14秒)
- 课时21:Explainable ML (5) (8分11秒)
- 课时22:Explainable ML (6) (7分26秒)
- 课时23:Explainable ML (7) (8分2秒)
- 课时24:Explainable ML (8) (7分15秒)
- 课时25:Life Long Learning (1) (13分50秒)
- 课时26:Life Long Learning (2) (7分24秒)
- 课时27:Life Long Learning (3) (12分3秒)
- 课时28:Life Long Learning (4) (4分38秒)
- 课时29:Life Long Learning (5) (3分18秒)
- 课时30:Life Long Learning (6) (14分14秒)
- 课时31:Life Long Learning (7) (11分33秒)
- 课时32:Meta Learning – MAML (1) (7分40秒)
- 课时33:Meta Learning – MAML (2) (7分51秒)
- 课时34:Meta Learning – MAML (3) (10分20秒)
- 课时35:Meta Learning – MAML (4) (5分13秒)
- 课时36:Meta Learning – MAML (5) (13分21秒)
- 课时37:Meta Learning – MAML (6) (6分31秒)
- 课时38:Meta Learning – MAML (7) (8分53秒)
- 课时39:Meta Learning – MAML (8) (5分10秒)
- 课时40:Meta Learning – MAML (9) (6分52秒)
- 课时41:Meta Learning - Gradient Descent as LSTM (1) (11分39秒)
- 课时42:Meta Learning - Gradient Descent as LSTM (2) (10分4秒)
- 课时43:Meta Learning - Gradient Descent as LSTM (3) (10分38秒)
- 课时44:Meta Learning – Metric-based (1) (10分29秒)
- 课时45:Meta Learning – Metric-based (2) (5分13秒)
- 课时46:Meta Learning – Metric-based (3) (11分28秒)
- 课时47:Meta Learning - Train+Test as RNN (7分46秒)
- 课时48:More about Auto-encoder (1) (13分38秒)
- 课时49:More about Auto-encoder (2) (6分10秒)
- 课时50:More about Auto-encoder (3) (12分28秒)
- 课时51:More about Auto-encoder (4) (14分51秒)
- 课时52:Network Compression (1) (8分22秒)
- 课时53:Network Compression (2) (12分42秒)
- 课时54:Network Compression (3) (8分31秒)
- 课时55:Network Compression (4) (6分36秒)
- 课时56:Network Compression (5) (11分51秒)
- 课时57:Network Compression (6) (13分7秒)
- 课时58:GAN (Quick Review) (38分3秒)
- 课时59:Flow-based Generative Model (1小时7分51秒)
- 课时60:Transformer (49分31秒)
- 课时61:ELMO, BERT, GPT (1小时4分51秒)
热门下载
热门帖子