Julien HerzeninUnit8 - Big Data & AIHierarchical Forecast Reconciliation with DartsPerform hierarchical reconciliation of forecasts very simply using the Darts open-source librarySep 28, 20222Sep 28, 20222
Julien HerzeninUnit8 - Big Data & AITransfer Learning for Time Series ForecastingWe explore training forecasting models on a large and diverse time series dataset, in order to forecast new series without training.May 5, 20223May 5, 20223
Julien HerzeninUnit8 - Big Data & AITime Series Forecasting Using Past and Future External Data with DartsBuilding models that are able to capture external data is often a key aspect of time series forecasting projects. For instance:Aug 13, 20212Aug 13, 20212
Julien HerzeninUnit8 - Big Data & AIBetter, Cheaper, Faster: How Artificial Intelligence Is Changing the Way of Discovering New…Advanced analytics and artificial intelligence (AI) are becoming increasingly important for the chemical industries. In the past, chemical…Mar 18, 2021Mar 18, 2021
Julien HerzeninUnit8 - Big Data & AITraining Forecasting Models on Multiple Time Series with DartsAny quantity varying over time can be represented as a time series: sales numbers, rainfalls, stock prices, CO2 emissions, Internet clicks…Feb 15, 20219Feb 15, 20219
Julien HerzeninUnit8 - Big Data & AIDarts: Time Series Made Easy in PythonTime series simply represent data points over time. They are thus everywhere in nature and in business: temperatures, heartbeats, births…Jun 29, 202016Jun 29, 202016
Julien HerzeninUnit8 - Big Data & AIRouting Traveling Salesmen on Random Graphs using Reinforcement Learning, in PyTorchEnd-to-end training of a neural network saying where to go nextFeb 15, 20203Feb 15, 20203
Julien HerzeninUnit8 - Big Data & AIComputing the Jacobian matrix of a neural network in PythonIn general, a neural network is a multivariate, vector-valued function looking like this:Nov 13, 20185Nov 13, 20185
