Extrapolation in Machine Learning
Tim discusses the concept of extrapolation in machine learning, emphasizing the importance of replicating information in different areas of ambient space for models to work effectively. The conversation delves into how CNNs use translational weight sharing to cheat in extrapolation by projecting patterns over the response map space.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#69 DR. THOMAS LUX - Interpolation of Sparse High-Dimensional Data
Related Questions