Deep Learning coverage.

WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition

Human Activity Recognition (HAR) using WiFi signals has emerged as a transformative technology for smart homes, healthcare monitoring, security systems, and ambient assisted living…

Why Deep Learning Works Even Though It Shouldn't

Why models always get better when they are bigger and deeper, even when the amount of data they consume stays the same or gets smaller.…

Writing High-Performance Kernels in TileLang, from GEMM to MLA

If you write GPU kernels, you live somewhere on a spectrum. At one end is Triton: quick to write,...…

HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection

While Deep Learning (DL) enhances automated electrocardiogram (ECG) analysis, clinical deployment is hindered by class imbalance and the generalization gap. This paper presents Hea…

Test-Time Deep Thinking to Explore Implicit Rules

With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by im…

Learning Abstractions: A Conversation with Yann LeCun

Uncovering the Latent Potential of Deep Intermediate Representations

Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric…

Enhancing Deep Neural Network Reliability with Refinement and Calibration

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This…

Multi-Gate Residuals

While Attention Residuals has shown some effectiveness in addressing the widespread issue of unbounded activation growth across deep residual layers, it inevitably incurs significa…

DeepSeek-V4 KV Cache Explained: Why 1M Context Uses Less VRAM

A comparison of DeepSeek-V4's CSA/HCA hybrid compressed attention with traditional MHA, GQA, and MLA, explaining why DeepSeek-V4 can greatly reduce KV Cache memory for 1M-token con…

Characterization of machine learning compilers for LLM inference on NVIDIA GPUs

AI inference is conflicted between Performance, developer Productivity, and device Portability–the P3 problem. Machine learning compilers (MLCs) aim to address this, but their ecos…

Shannon Got AI This Far. Kolmogorov Shows Where It Stops

Shannon Got AI This Far. Kolmogorov Shows Where It Stops. This post previewed a conversation I recorded with Martin Casado for the a16z podcast. The ideas here came up in that disc…

The Brain vs. Deep Learning Part I: Computational Complexity

This blog post compares deep learning to the brain and derives an estimate of computational power for the brain which is used to predict the singularity.…

A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imagery

COVID-19 was a significant challenge that led to the loss of numerous lives daily. Not only a certain country was involved in this outbreak, but even the world has suffered because…

Pixel Wised Lesion Prediction on COVID-19 CT Imagery: A Comparative Analysis of Automated Image Segmentation Architectures

In recent years, there has been a notable increase in the level of attention that is given to algorithms based on deep learning in the context of medical image segmentation. Nevert…

From SGD to Muon: Adaptive Optimization via Schatten-p Norms

Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. …

RAG-based EEG-to-Text Translation Using Deep Learning and LLMs

The decoding of linguistic information from electroencephalography (EEG) signals remains an extremely challenging problem in brain-computer interface (BCI) research. In particular,…

Uncertainty-Aware Wildfire Smoke Density Classification from Satellite Imagery via CBAM-Augmented EfficientNet with Evidential Deep Learning

Rapid and accurate wildfire smoke severity assessment from satellite images is essential for emergency response, air quality modeling, and human health risk management. Existing de…

Softmax in front of CrossEntropyLoss: 16 other bugs PyTorch won't catch

A walkthrough of the 17-rule design-time linter inside Neurarch: what each rule catches, why it matters, and where static analysis stops being useful for neural networks.…

"Deep Generative Modeling": Introductory Examples

"Deep Generative Modeling": Introductory Examples. Contribute to jmtomczak/intro_dgm development by creating an account on GitHub.…

Distance Marching for Generative Modeling

Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and…

Chain-of-Thought and Beyond: How LLMs Actually Learn to Reason

"The ability to reason step-by-step is not just a feature. It might be the difference between a...…

Making Deep Learning Go Brrrr from First Principles

PyTorch NaNs Are Silent Killers — So I Built a 3ms Hook to Catch Them at the Exact Layer

NaNs don’t crash your training — they quietly destroy it. After losing hours to a silent failure in a ResNet training run, I built a lightweight detector that pinpoints the exact l…