Learn how to apply modern machine learning methods to ecological time-series data in our live online course Machine Learning for Time Series Using R (METR01). https://prstats.org/course/machine-learning-for-ecological-time-series-metr01/ This applied R training is designed for scientists who want practical skills for analysing, modelling, and forecasting time-series data using reproducible workflows. Participants will work through hands-on examples to understand how machine learning approaches can be used to detect patterns, make predictions, and interpret complex ecological dynamics. The course covers: Preparing and structuring time-series data Supervised and unsupervised machine learning approaches Model training, validation, and performance assessment Forecasting trends and dynamics Interpreting machine learning outputs The training is delivered via recordings available 30 days before the course and supported by 5 x live Q and A sessions from 13-17 April. You also have access for 30 days after the course to revisit any materials. Course details Dates: 13'17 April 2026 Duration: 5 days, approximately 7 hours per day Format: Recorded sessions with live Q&A Fee: pounds 450 This course is suitable for postgraduate students, researchers, consultants, and professionals working with ecological monitoring data, population time series, sensor data, or environmental datasets who want to apply machine learning techniques in R. Full details and registration: https://prstats.org/course/machine-learning-for-ecological-time-series-metr01/ Email oliver@prstats.org with any questions -- Oliver Hooker PhD. PR stats ---- Build practical deep learning skills in Python with our live online course Deep Learning Using Python(DLUP01). https://prstats.org/course/deep-learning-using-python-dlup01/ This intensive two-day workshop provides a structured introduction to deep learning and its implementation in Python using PyTorch. Participants learn both the theoretical foundations of neural networks and how to build modern deep learning models through hands-on coding exercises. The course covers: Foundations of artificial neural networks and deep learning Training networks using backpropagation and optimisation methods Building multilayer perceptrons in PyTorch Convolutional neural networks for image data Transformer architectures and minimal GPT-style models Using pre-trained models with the Hugging Face Transformers library () Delivered live online with recordings available, participants receive course materials, datasets, and post-course support. Course details Dates: 14-15 April 2026 Duration: 2 days, approximately 6 hours per day Format: Live online Fee: 300 This course is suitable for researchers, data scientists, and professionals who are comfortable with Python and want a clear, practical introduction to neural networks, CNNs, and transformer models for real research problems. () Full details and registration: https://prstats.org/course/deep-learning-using-python-dlup01/ Email oliver@prstats.org with any questions -- Oliver Hooker PhD. PR stats Oliver Hooker (to subscribe/unsubscribe the EvolDir send mail to golding@mcmaster.ca)