deep learning
PulseAugur coverage of deep learning — every cluster mentioning deep learning across labs, papers, and developer communities, ranked by signal.
- instance of convolutional neural network 95%
- instance of alphaXiv 90%
- used by magnetic resonance imaging 90%
- used by Alzheimer's disease 90%
- instance of supervised learning 90%
- used by stochastic gradient descent 80%
- used by alphaXiv 70%
- used by convolutional neural network 70%
- used by ScienceCast 70%
- developed by magnetic resonance imaging 70%
- instance of ScienceCast 70%
- instance of Gotit.pub 70%
- 2026-06-09 research_milestone A new deep learning pipeline was presented for assisting in the diagnosis of acute myeloid leukemia. source
27 day(s) with sentiment data
-
New method injects biokinetic knowledge into neural networks for data-scarce bioprocess modeling
Researchers have developed a novel approach to address data scarcity in bioprocess modeling for drug discovery and biomanufacturing. Their work systematically explores methods for integrating existing biokinetic knowled…
-
New Receptron model offers hardware-aware edge intelligence for IoT
Researchers have developed a novel neuromorphic-inspired classifier called the Receptron model, designed to overcome the computational and memory limitations of microcontroller units (MCUs) for edge intelligence in IoT …
-
New Probabilistic Residual Learning enhances recommender systems
Researchers have introduced Probabilistic Residual Learning (PRL), a novel causal Bayesian recommendation model designed to enhance existing deep learning recommender systems. PRL addresses the complexity and black-box …
-
Neural Networks Explained: A Simple Guide Inspired by the Human Brain
This article explains the fundamental concepts of neural networks, drawing parallels to the human brain's structure of neurons and synapses. It breaks down the three main layers—input, hidden, and output—detailing their…
-
New AI framework maps crop germination gaps using drone imagery
Researchers have developed a deep learning framework called CGMap to precisely map crop germination gaps using drone imagery. This system, which utilizes the YOLOv8 architecture, identifies germinated plants and "bald s…
-
Diffusion models generate synthetic EEG data to improve hearing aid attention decoding
Researchers have developed a method using diffusion probabilistic models (DPMs) to generate synthetic electroencephalogram (EEG) data for auditory attention decoding (AAD) in hearing aids. This approach addresses the ch…
-
New PhenSPINE benchmark advances spine pathology diagnosis with deep learning
Researchers have introduced PhenSPINE, a new benchmark dataset for diagnosing spinal pathologies using Magnetic Resonance Imaging (MRI). The dataset contains 16,813 images from 250 patients and incorporates deep learnin…
-
Author details 300-hour deep dive into ML, data science, and MLOps
The author details their intensive 300-hour journey into mastering machine learning, data science, deep learning, and MLOps. They emphasize that beginners often struggle not from laziness, but from a lack of clear guida…
-
New deep learning models decode visual perception from brain activity
Researchers have developed new deep learning approaches for decoding visual semantic information from brain activity. One study utilizes an end-to-end Transformer-based deep learning framework with electrocorticography …
-
New unsupervised method enables AI to learn new visual classes from unlabeled data
Researchers have developed a new method called ICPL (Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels) that enables deep learning models to learn new classes from unlabeled data in computer vision …
-
New deep learning framework enhances adversarial robustness via geometry
A new geometry-aware deep learning framework has been developed to address the challenge of balancing training accuracy with adversarial robustness. This framework utilizes layer-wise local training to refine internal n…
-
Deep learning framework enhances lung ultrasound video classification
Researchers have developed a deep learning framework for classifying lung ultrasound videos, aiming to improve automated analysis of this bedside diagnostic tool. The framework incorporates hierarchy-aware training and …
-
Economists develop theoretical framework for pre-trained embeddings
Researchers have developed a theoretical framework for using pre-trained deep learning embeddings in econometrics, addressing challenges where models are trained on different datasets or tasks. The paper provides condit…
-
Deep learning theory papers explore convergence and Lipschitz continuity
Two recent arXiv papers delve into theoretical aspects of deep learning, focusing on convergence and Lipschitz continuity. The first paper by Noboru Isobe explores an idealized continuous-depth model for deep neural net…
-
New AI framework identifies dark vessels using SAR images and GT estimation
Researchers have developed a novel framework to identify "dark vessels" that disable their transponders for surveillance evasion. The system combines a multi-task deep learning model to predict vessel location, type, an…
-
Understanding Tensors: The Core Data Structure in AI
A tensor is a fundamental data structure in machine learning and deep learning, representing multi-dimensional arrays. These arrays are crucial for organizing and processing the vast amounts of data used in training com…
-
AI, ML, Deep Learning, GenAI, Agentic AI: Understanding the Hierarchy
The terms AI, Machine Learning, Deep Learning, Generative AI, and Agentic AI are often used interchangeably but represent a hierarchy of nested concepts. Artificial Intelligence is the broadest goal of enabling machines…
-
New research details backdoor attacks and defenses for speech recognition models
Two new research papers explore the vulnerabilities of speech recognition models to backdoor attacks. The first paper introduces SpeechGuard, a system designed to detect and neutralize these attacks in real-time by iden…
-
Geoffrey Hinton: AI Pioneer Revolutionized Neural Networks
Geoffrey Hinton, a prominent figure in the field of artificial intelligence and often referred to as the 'Godfather of AI,' is recognized for his groundbreaking work on neural networks and deep learning. As a computer s…
-
Survey paper details deep learning methods for single-cell RNA sequencing analysis
A survey paper has been published detailing the application of deep learning techniques to single-cell RNA sequencing (scRNA-seq) analysis. The paper comprehensively reviews 25 distinct methods across six subcategories,…