Member-only story
In my most recent post, I carried out a review of a research paper where a RNN-LSTM was used to predict on bitcoin prices, and that post can be read here:- https://medium.com/@tracyrenee61/research-paper-review-bitcoin-price-prediction-using-rnn-and-lstm-5d1aef9804f7
In the research paper in question, it was suggested that a different deep learning model, such as a convolutional neural network (CNN) could be used to try to improve the predictions.
A CNN is a type of deep learning neural network architecture commonly used in computer vision.
CNNs consist of multiple layers, such as the input layer, convolutional layer, pooling layer, and fully connected layers.
The convolutional layer applies to filters to the input image to extract features, the pooling layer downsamples the image to reduce computation, and the fully connected layer makes the final prediction. The network learns the optimal filters through backpropagation and gradient descent.
Although traditionally developed for 2D image data, CNNs can be used to model univariate time series forecasting problems.
Univariate time series of observations with a temporal ordering and a model is required to learn from the series of past observations to predict the next value…
