Join us for the latest from the Cloudera Fast Forward research team. This webinar will cover two recent research reports.
Meta-learning: Learning to learn
In contrast to how humans learn, deep learning algorithms need vast amounts of data and compute and may yet struggle to generalize. Humans are successful in adapting quickly because they leverage knowledge acquired from prior experience when faced with new problems. In this webinar we will explain how meta-learning can leverage previous knowledge acquired from data to solve novel tasks quickly and more efficiently during test time. We’ll cover:
when you should think about meta-learning and lessons to apply in your data science practice
how meta-learning helps models to generalize to new circumstances or classes during inference
a foundational approach to the kind of problems it can help us solve, along with our experimental results
Structural time series for long term forecasting
Time series data is ubiquitous, and forecasting has a long history. Still, novel methods continue to be developed. Generalized additive models give us a simple, flexible and interpretable means for modeling some classes of time series, especially where there is seasonality. We look at the benefits and trade-offs of taking a curve-fitting approach to time series, and demonstrate its use via Facebook's Prophet library on a demand forecasting problem. In particular, we'll cover:
how capturing the uncertainty in time series allows us to ask better questions
the importance of baseline models, and how to develop models iteratively
the benefits to treating analysis as a product, and building tools to aid it
As always, we’ll discuss the challenges and applications presented by the techniques in both reports, and answer all your questions on our live webinar. We look forward to seeing you there!
Speakers

Nisha Muktewar
