Foundations of Deep Learning: From Nearest Neighbors to Transformers
Nearest Neighbor and k-NN Classifiers
The Nearest Neighbor classifier stores the entire training set and predicts labels by finding the closest training example using a distance metric like L1 (Manhattan) or L2 (Euclidean). While simple, it suffers from high prediction latency (O(n)) and large memory usage.
class KNearestNeighbor:
def init(sel ...
Posted on Mon, 25 May 2026 19:10:33 +0000 by suigion
ESPNet Series: Efficient CNN Architecture for High-Resolution Semantic Segmentation
This article presents the ESPNet series, a specialized network architecture designed for semantic segmentation of high-resolution images. The framework achieves remarkable efficiency in computational complexity, memory footprint, and power consumption. The core contribution lies in the Efficient Spatial Pyramid (ESP) module, which forms the fou ...
Posted on Sun, 17 May 2026 04:00:33 +0000 by Incredinot