Skip to content
Tagged articles

Residual Networks

5 articles · Page 1 of 1
IT Services Circle
IT Services Circle
Oct 17, 2026 · Artificial Intelligence

TCN Deep Dive: Causal & Dilated Convolutions for Long-Range Time Series Forecasting

This article explains Temporal Convolutional Networks (TCN) for time series forecasting, detailing how causal and dilated convolutions capture long-range dependencies without future leakage, and demonstrates with a complete PyTorch implementation comparing shallow (61h receptive field) vs deep (253h) models on synthetic order data with daily, weekly, and promotional patterns.

Causal ConvolutionDilated ConvolutionPyTorch
0 likes · 16 min read
TCN Deep Dive: Causal & Dilated Convolutions for Long-Range Time Series Forecasting
Data Party THU
Data Party THU
Apr 3, 2026 · Artificial Intelligence

Can Attention Replace Residuals? Inside the New Attention Residuals Breakthrough

The article reviews the Kimi team's Attention Residuals approach, which substitutes traditional ResNet additive shortcuts with learned attention‑based weighting, explains the theoretical motivation linking depth to time, details full‑attention and block‑wise implementations, presents experimental results showing up to 1.25× compute efficiency and improved performance on reasoning and knowledge tasks.

Attention MechanismModel EfficiencyResidual Networks
0 likes · 11 min read
Can Attention Replace Residuals? Inside the New Attention Residuals Breakthrough
DataFunTalk
DataFunTalk
Dec 25, 2019 · Artificial Intelligence

Exploring Depth in Graph Convolutional Networks (GCN): Architecture, Experiments, and Future Work

This article examines the challenges of deepening Graph Convolutional Networks (GCN), introduces ResGCN, DenseGCN, and skip‑neighbor designs to enable deeper architectures, presents experimental results showing improved performance with 28‑layer models, and outlines future research directions.

GCNGraph Neural NetworksResidual Networks
0 likes · 7 min read
Exploring Depth in Graph Convolutional Networks (GCN): Architecture, Experiments, and Future Work
Alibaba Cloud Developer
Alibaba Cloud Developer
Aug 26, 2016 · Artificial Intelligence

ICML Tutorial Highlights: Deep Residual Nets, Stochastic Gradient, Deep RL

At the ICML pre‑conference tutorial, experts presented deep residual networks, stochastic gradient methods for large‑scale learning, and deep reinforcement learning, highlighting architectural innovations, optimization theory, noise‑reduction techniques, and practical considerations for building scalable, high‑performance AI models.

Residual Networksdeep learningstochastic gradient
0 likes · 14 min read
ICML Tutorial Highlights: Deep Residual Nets, Stochastic Gradient, Deep RL