filmov
tv
Explainable AI with H2O Driverless AI's Machine Learning Interpretability Module by Martin Dvorak
Показать описание
Abstract:
Artificial intelligence and machine learning present significant opportunities to businesses. To reap the full benefits of ML, organizations need to trust the algorithms and incorporate them into their existing workflows. Transparency, accountability, and trustworthiness of data-driven decision support systems based on AI and machine learning are serious regulatory mandates in banking, insurance, healthcare, and other industries. From pertinent regulations to increasing customer trust, data scientists and business decision-makers must show that AI-based decisions can be explained. H2O Driverless AI does explainable AI today with its machine learning interpretability (MLI) module. This capability in H2O Driverless AI employs a unique combination of techniques and methodologies to explain the results of both Driverless AI models and external models.
About Martin:
Martin is a passionate software engineer who is interested in machine learning, knowledge management and virtual machine construction. He holds a Master's degree in Computer Science from Charles University Prague with specializations in AI/ML, compilers and operating systems. Martin is the lead software engineer of the MLI team at H2O.ai.
H2O Driverless AI:
Artificial intelligence and machine learning present significant opportunities to businesses. To reap the full benefits of ML, organizations need to trust the algorithms and incorporate them into their existing workflows. Transparency, accountability, and trustworthiness of data-driven decision support systems based on AI and machine learning are serious regulatory mandates in banking, insurance, healthcare, and other industries. From pertinent regulations to increasing customer trust, data scientists and business decision-makers must show that AI-based decisions can be explained. H2O Driverless AI does explainable AI today with its machine learning interpretability (MLI) module. This capability in H2O Driverless AI employs a unique combination of techniques and methodologies to explain the results of both Driverless AI models and external models.
About Martin:
Martin is a passionate software engineer who is interested in machine learning, knowledge management and virtual machine construction. He holds a Master's degree in Computer Science from Charles University Prague with specializations in AI/ML, compilers and operating systems. Martin is the lead software engineer of the MLI team at H2O.ai.
H2O Driverless AI:
0:47:24
0:07:32
0:56:02
0:27:39
1:00:21
0:40:35
0:06:02
0:00:39
0:59:25
0:19:00
0:02:17
0:43:50
0:03:49
0:01:01
0:04:36
0:55:35
0:03:41
0:57:08
0:00:34
0:58:01
0:57:29
1:01:17
0:02:57
0:06:15