Tagged articles
loss function
14 articles · Page 1 of 1
A TPAMI 2026 survey uses autocorrelation modeling as a unified lens to categorize ten years of time-series forecasting advances, covering backbone architectures (RNN, CNN, Transformer, Mamba, LLM alignment) and loss functions (likelihood-based, shape alignment, distribution alignment, conditional generation), plus future research directions.
Surveyautocorrelation modelingbackbone architecture
0 likes · 21 min read

This article breaks down the fundamentals of large model training—covering data, parameters, neural networks, loss functions, gradient descent, pre‑training, and fine‑tuning—in plain language so readers can grasp how massive models learn without needing to dive into complex mathematics.
Gradient DescentModel TrainingPretraining
0 likes · 12 min read

The paper identifies two fundamental issues in time‑series forecasting—label autocorrelation bias and task‑scale explosion caused by the standard TMSE loss—and proposes Time‑o1, a PCA‑based orthogonal label transformation that eliminates bias, reduces optimization complexity, and yields consistent performance gains across multiple models and datasets.
NeurIPS 2025PCATime‑o1
0 likes · 12 min read


Qborfy AIJul 3, 2025 · Artificial Intelligence
This article explains what loss functions are, outlines their three essential components, categorizes them for regression, classification, and generation tasks, reviews five classic loss functions with their noise resistance and gradient traits, and offers practical guidelines for selecting the right loss for AI models.
AI FundamentalsClassificationdeep learning
0 likes · 4 min read

This article analyzes the VA‑VAE approach that aligns visual tokenizers with vision foundation models to resolve the reconstruction‑generation trade‑off in latent diffusion models, detailing the VF loss design, adaptive weighting, LightningDiT enhancements, experimental setup, and state‑of‑the‑art ImageNet performance.
LightningDiTVAEVision Foundation Model
0 likes · 16 min read

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.
Gradient DescentMNISTdeep learning
0 likes · 16 min read

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.
AI basicsGradient Descentlinear regression
0 likes · 13 min read


NewBeeNLPDec 3, 2024 · Artificial Intelligence
The article reflects on open‑source LLMs like Qwen2 and Llama 3.1, questioning whether models should self‑review answers, how hidden states might signal uncertainty, the role of loss‑function design, scaling laws, and the trade‑offs between PPO and DPO in alignment.
Scaling LawSelf-Correctionlarge language models
0 likes · 9 min read

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.
ClassificationOne-hot encodingcross-entropy
0 likes · 5 min read

This article uses a narrative of an AI neuron to explain fundamental concepts of neural networks, including neuron structure, weighted sums, activation functions, loss functions, gradient descent, and learning rate, making complex AI topics accessible to beginners.
AI basicsGradient DescentNeural Network
0 likes · 9 min read

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.
AIBilibilideep learning
0 likes · 16 min read

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.
Newton's lawhypothesis spaceloss function
0 likes · 15 min read

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.
classification modelloss functionmachine learning
0 likes · 10 min read

Meituan’s delivery ETA system progressed from linear regression to DeepFM, enriching user, rider, merchant, and spatiotemporal features, employing an asymmetric loss and business‑rule integration to favor early arrivals, adding a tail‑adjustment term, and is engineered with Spark‑assembled TFRecords, multi‑GPU TensorFlow training, and remote‑served TensorFlow Java inference achieving sub‑5 ms TP99 latency.
ETALong TailTensorFlow Serving
0 likes · 15 min read
