Transformers have revolutionized Natural Language Processing and powered significant improvements in areas such as neural machine translation, classification and named entity recognition. Initially transformers were slow to catch in on in the time series domain. However, over the last year and a half a number of transformer variations for time series classification and forecasting have emerged. We have seen models like the Temporal Fusion Transformers, Convolutional Transformers, Dual Stage Attention and more attempt break into time series. The latest model the Informer builds upon this trend while incorporating several novel components.
Flow Forecast, a deep learning for time series forecasting…
Deploying machine learning models remains a sticking point for many companies and time series forecasting models are no exception. According to VentureBeat around 90% of models never make it into production. While there might be many reasons for this (e.g. models were exploratory in nature and the end goal was never production, etc) suffice to say that many promising models are shelved at this stage. This is especially true of deep learning models that often have many moving parts.
I’m excited to announce that today we are releasing Flow Forecast version 0.95 (if you are unfamiliar with Flow Forecast please see the introductory article). Although we are still somewhat far away from version 1.0 there are a lot of cool new features now available. To get the latest version please run
pip install flood_forecast --upgrade. You can also go to our
Over the past year I’ve used Flow Forecast to train hundreds of PyTorch time series forecasting models on a wide variety of datasets (river flow, COVID-19, solar/wind power, and stock prices). Often beginners come to me looking for info what they should do first. This article is a brief breakdown of some basic tips that you can use when training a time series forecasting model.
I frequently see a lot of different terms thrown around with respect to time series ML techniques. Here I will attempt to clarify them:
This year at the Neural Information Processing Conference, authors published a number of new papers focusing on time series forecasting and classification. Here I will briefly review their major contributions as well as discuss their implementation and our timeline for porting them to our deep learning for time series forecasting framework flow-forecast.
As the creator/maintainer of an open-source framework, both myself and our core contributors have to constantly weigh the time necessary to add new models and methods versus the benefits for our end users. At flow forecast, as a framework that serves both businesses and researchers, we have…
A brief history: ImageNet was first published in 2009 and over the next four years would go on to form the bedrock of most computer vision models. To this day whether you are training a model to detect pneumonia or classify models of cars you will probably start with a model pre-trained on ImageNet or some other large (and general image) dataset.
More recently papers like ELMO and BERT (2018) leveraged transfer learning to effectively improve performance on several NLP tasks. These models create effective context dependent representations of words. …
Note this is roughly based on a presentation I made back in February at the Boston Data Science Meetup Group. You can find the full slide deck here. I have also included some more recent experiences and insights as well as answers to common questions that I have encountered.
When I first started my river forecasting research, I envisioned using just a notebook. However, it became clear to me that effectively tracking experiments and optimizing hyper-parameters would play a crucial role in the success of any river flow model; particularly, as I wanted to forecast river flows for over 9,000+…
Scrum is a popular methodology for PM in software engineering and recently the trend has carried over to data science. While the utility of Scrum in standard software engineering may remain up for debate, here I will detail why it has unquestionably no place in data science (and data engineering as well). …
Flow Forecast is a recently created open-source framework that aims to make it easy to use state of the art machine learning models to forecast and/or classify complex temporal data. Additionally, flow-forecast natively integrates with Google Cloud Platform, Weights and Biases, Colaboratory, and other tools commonly used in industry.
Note from the editors: Towards Data Science is a Medium publication primarily based on the study of data science and machine learning. We are not health professionals or epidemiologists, and the opinions of this article should not be interpreted as professional advice. To learn more about the coronavirus pandemic, you can click here.
With COVID-19 sweeping across the world, and people (particularly Americans) anxious to get back to work, now more than ever we need models to effectively forecast the spread of COVID-19. However, at present many models have performed poorly at estimating the disease spread and the overall impacts…
Deep learning researcher. Creator/Maintainer of @FlowTemporal