Glad to hear, and thanks for the constructive feedback! Likewise, it was a lot of fun to write these. I will make sure to do the yearly paper-roundup on a yearly basis 😊
Many thanks for the post, insightful as always. Could you comment on developments in time-series modelling and prediction? Do you think this field has matured? I am especially interested in multivariate time-series modelling but I don't see many progress updates in this field.
Glad you liked it! I am not working on time series problems, but I think that matrix profiles have become the go-to as feature inputs in recent years. There are also interesting developments in the deep tabular domain that I summarized here: https://sebastianraschka.com/blog/2022/deep-learning-for-tabular-data.html. It will be interesting to transfer these methods to time series data.
For those who are wondering about Ahead of AI #5 ... it's coming out Monday! Just putting on some final polish (and shortening it a bit), and then it's good to go :)
Awesome summary for 2022! I really enjoyed you inputing your thoughts for each paper! Already looking forward to 2023 summary 😁
Glad to hear, and thanks for the constructive feedback! Likewise, it was a lot of fun to write these. I will make sure to do the yearly paper-roundup on a yearly basis 😊
Many thanks for the post, insightful as always. Could you comment on developments in time-series modelling and prediction? Do you think this field has matured? I am especially interested in multivariate time-series modelling but I don't see many progress updates in this field.
Glad you liked it! I am not working on time series problems, but I think that matrix profiles have become the go-to as feature inputs in recent years. There are also interesting developments in the deep tabular domain that I summarized here: https://sebastianraschka.com/blog/2022/deep-learning-for-tabular-data.html. It will be interesting to transfer these methods to time series data.
thank you, will refer to the link.
For those who are wondering about Ahead of AI #5 ... it's coming out Monday! Just putting on some final polish (and shortening it a bit), and then it's good to go :)
Really fantastic and clear summaries of the top paper, thanks and keep them coming!