In this project we have explored the use of imaging time series to enhance forecasting results with Neural Networks. The approach has revealed itself to be extremely promising as, both in combination with an LSTM architecture and without, it has out-performed the pure LSTM architecture by a solid margin within our test datasets.
deep-learning
series
convolutional-layers
matplotlib
eth-zurich
predictions
ethz
convolutional-lstm
time-series-forecasting
tensorflow2
conv-lstm
holt-winter
conv-mlp
lstm-architecture
-
Updated
Jul 6, 2023 - Python