1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jeff Roach

PyData LA 2018
This talk describes an experimental approach to time series modeling using 1D convolution filter layers in a neural network architecture. This approach was developed at System1 for forecasting marketplace value of online advertising categories.
Slides - www.slideshare.net/PyData/1d-...
---
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our KZbin videos to help with discoverability? Find out more here: github.com/numfocus/KZbinVi...

[@Dr.R.K.Verma_ABST]

on 7:08 one layer of filters has n*(n+1)/2= 6*(6+1)/2 = 6*7/2= 21 otherwise this will be one layer of filters n*(n-1)/2= 6*(6-1)/2 = 6*5/2 = 15

[@alexanderskusnov5119]

Why did you change the order: pool, relu instead of relu, pool?

[@zxynj]

7:30 I think one layer is 21 weights.

[@Jeff-qw2de]

I think so too. Lately, the academic community in computing seems to confuse people and offer no explanation