Geometry of Neural Networks
Thomas discusses how neural networks can be viewed as piecewise linear approximations, drawing parallels to traditional machine learning algorithms. He emphasizes the importance of provable error bounds and the connection between neural networks and Delaunay triangulation for consistent approximation techniques.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#69 DR. THOMAS LUX - Interpolation of Sparse High-Dimensional Data
Related Questions