Joseph Pemberton

This work extensively evaluates time series forecasting models, focusing on individual algorithms and hybrid combinations. The study explores the forecasting capabilities across five diverse time series, comprising financial indicators and climatic variables. The models considered include autoregressive integrated moving average (ARIMA), exponential smoothing (ES), singular spectrum analysis (SSA), and Long Short-Term Memory (LSTM), along with hybrid variations. The hybrid time series models demonstrate superior performance by enhancing forecasting accuracy in most of the scenarios. The models SSA-LSTM-LSTM, SSA-R-LSTM, and SSA-ARIMA-LSTM perform well for the stock exchange rate, NASDAQ Composite Index, and solar radiation data, respectively. These hybrid approaches leverage the strengths of diverse algorithms, showcasing adaptability, robustness, and flexibility in handling various time series patterns. A short-term daily forecasting scenario provides insights into short-term predictive capabilities, highlighting the effectiveness of hybrid models in capturing rapid fluctuations. The study contributes valuable insights for researchers and practitioners seeking optimal time series forecasting strategies based on specific data characteristics and forecasting requirements.

The brain must maintain a stable world model while rapidly adapting to the environment, but the underlying mechanisms are not known. Here, we posit that cortico-cerebellar loops play a key role in this process. We introduce a computational model of cerebellar networks that learn to drive cortical networks with task-outcome predictions. First, using sensorimotor tasks, we show that cerebellar feedback in the presence of stable cortical networks is sufficient for rapid task acquisition and switching. Next, we demonstrate that, when trained in working memory tasks, the cerebellum can also underlie the maintenance of cognitive-specific dynamics in the cortex, explaining a range of optogenetic and behavioural observations. Finally, using our model, we introduce a systems consolidation theory in which task information is gradually transferred from the cerebellum to the cortex. In summary, our findings suggest that cortico-cerebellar loops are an important component of task acquisition, switching, and consolidation in the brain.