A Deep-Q Network (DQN) is a reinforcement learning technique that attempts to model the actions that perform best in each state in real-time.
Chatbots offer another user-friendly conversational interface to the entire SAS Viya ecosystem, bringing together reporting capabilities, analytics and artificial intelligence.
The recently released 2021 Gartner MQ for Data Science and Machine Learning contains a wealth of information and here are my takes on key market trends from that report for data scientists. This evaluation features SAS Viya with its SAS Data Science offerings.
By making requests through API calls you can expand the functionality of the bots you make with SAS Conversation Designer; allowing your bots to query external sources for up-to-date information, score a model, and many other possibilities. This is very beneficial as SAS Conversation Designer is included in many offerings of the modernized SAS Viya platform, meaning you can easily create bots that are integrated with the other services of the SAS Viya platform or third-party services.
Note from Udo Sglavo: In our peace of mind blog series, we documented areas of analytics that are either evolving or not necessarily in the standard toolset of data scientists. We looked at causal modeling, network analytics, and econometrics, to name a few. With this blog post, we would like
Note from Udo Sglavo on mathematical optimization: When data scientists look at the essence of analytics and wonder about their daily endeavor, it often comes down to supporting better decisions. Peter F. Drucker, the founder of modern management, stated: "Whenever you see a successful business, someone once made a courageous decision."
A note from Udo Sglavo: When people ask me what makes SAS unique in the area of analytics, I will mention the breadth of our analytic portfolio at some stage. In this blog series, we looked at several essential components of our analytical ecosystem already. It is about time to
A good public transportation system is crucial to develop smart cities, particularly in great metropolitan areas. Network optimization algorithms can be applied to better understand urban mobility, particularly based on a multimodal public transportation network.
A note from Udo Sglavo: This post offers an introduction to complex optimization problems and the sophisticated algorithms SAS provides to solve them. In previous posts of this series, we learned that data availability, combined with more and cheaper computing power, creates an essential opportunity for decision-makers. After looking at network analytics
In this article, we summarize our SAS research paper on the application of reinforcement learning to monitor traffic control signals which was recently accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada. This annual conference is hosted by the Neural Information Processing Systems Foundation, a non-profit corporation that promotes the exchange of ideas in neural information processing systems across multiple disciplines.
