Accurate forecasting of COVID-19 spread plays an essential role in improving the management of the overcrowding problem in hospitals and enables appropriate optimization of the available resources (i.e., materials andstaff). The goal of this project is to apply deep learning methods (e.g., LSTM, BiLSTM) for COVID-19 transmission forecasting. The performance of the investigated deep learning models will be tested using confirmed and recovered COVID-19 cases time-series data from some impacted countries, including Brazil, France, India, Saudi Arabia, and the US.