1 views collected around this technical thread.
This article explains how neural networks learn by using labeled training data, describing the role of weights, biases, activation functions, and how gradient descent iteratively adjusts parameters to minimize loss, illustrated with the MNIST digit‑recognition example.
This article uses a dialogue format to introduce the fundamentals of linear regression, explain how loss functions such as mean squared error quantify prediction errors, and describe gradient descent as an iterative optimization technique for finding the best model parameters, illustrated with simple numeric examples and visual aids.
This article explains how loss functions evaluate model performance, contrasts regression’s mean squared error with classification’s cross‑entropy, describes one‑hot encoding and softmax outputs, and shows why higher predicted probabilities for the correct class yield lower loss, highlighting applications in image, language, and speech tasks.
Bilibili’s self‑supervised video super‑resolution system upgrades low‑resolution streams to 4K by using three parallel degradation‑branch networks—texture‑enhancing, line‑recovering, and noise‑removing—tailored to anime, game, and real‑world content, delivering sharper edges, finer textures, and measurable quality gains across its online playback pipeline.
This article illustrates how a machine can rediscover Newton’s second law by treating force and acceleration data as a simple linear regression problem, detailing the three fundamental steps of hypothesis space definition, loss function design, and optimization through calculus or gradient methods.
This article examines the differences and similarities between classification (pointwise) and ranking (pairwise) models for recommendation systems, covering their probabilistic foundations, loss functions, parameter updates, and practical implications such as sensitivity to statistical features and robustness.