Robust Deep Learning Under Distribution Shift
Explore deep learning challenges under distribution shift, covering adversarial attacks, label shift detection, and domain adaptation techniques for robust model performance in real-world scenarios.
Interpretability - Now What?
Explore machine learning interpretability methods, focusing on Testing with Concept Activation Vectors (TCAV) and its applications in image prediction and medical diagnosis.
Inversion of 2D Remote Sensing Data to 3D Volumetric Models Using Deep Dimensionality Exchange
Innovative deep learning approach for inverting 2D remote sensing data to 3D models, reducing computation time from months to milliseconds. Explores unique embedding strategies and model architectures for efficient volumetric space reconstruction.
The Software GPU - Making Inference Scale in the Real World
Discover how to achieve GPU-level performance for deep learning inference using only software on commodity CPUs, challenging conventional wisdom and offering a cost-effective, flexible solution for scaling AI models.
Learning with Limited Labels - ODSC West 2020
Explore advanced techniques for machine learning with limited labeled data, including domain adaptation, few-shot learning, and self-supervised learning to enhance model performance across diverse domains and novel categories.
Deep Learning Survival Analysis for Consumer Credit Risk Modelling
Explore deep learning survival analysis for precise credit risk prediction in consumer lending, combining traditional methods with advanced techniques for improved time-to-event forecasting.
Recent Advances in Machine Learning with Applications to Internet of Things - Adam McElhinney
Explore machine learning advancements in IoT, covering failure prediction, data challenges, and real-world applications. Learn about deep learning, transfer learning, and future opportunities in this rapidly evolving field.
Towards Deep Learning Models Resistant to Adversarial Attacks
Explore deep learning model vulnerabilities and defense strategies against adversarial attacks, examining research findings and experimental results.
YOLOv4 - Optimal Speed and Accuracy of Object Detection
Explore YOLOv4's advancements in object detection, including improved speed and accuracy, new activation functions, and spatial attention mechanisms.
MAST - A Memory-Augmented Self-Supervised Tracker
Learn about MAST, a novel memory-augmented self-supervised tracker that enhances video tracking and segmentation using attention mechanisms and innovative algorithms.
Deep Ensembles: A Loss Landscape Perspective
Explore deep ensemble learning through loss landscapes, examining function similarity, subspace sampling, and prediction space analysis for improved model performance.
Exploring the Origins and Prevalence of Texture Bias in Convolutional Neural Networks
Explore texture bias in CNNs: origins, prevalence, and implications. Examine dataset influence, training objectives, and model architectures to understand and mitigate this phenomenon in computer vision.
Fraud Detection in Bitcoin Payment Networks
Explore fraud detection in Bitcoin networks using machine learning, covering techniques like deep learning and entity recognition for effective cryptocurrency security.
Deep Dive into the Transformer Encoder Architecture
Detailed exploration of transformer encoder architecture, covering embeddings, positional encodings, self-attention mechanisms, and key components for effective natural language processing.
CI-CD for Machine Learning
Automate ML model training and evaluation using GitLab CI/CD. Learn to allocate cloud instances, generate performance reports, transfer data, and customize workflows for efficient machine learning development.
Deep Learning and Software Engineering - A Retrospective and Paths Forward
Explore deep learning's impact on software engineering, including code suggestion and program repair. Discover current research, challenges, and future directions in this emerging field.
Learning Symbolic Equations with Deep Learning
Explore deep learning techniques to extract symbolic equations from Graph Neural Networks, with applications in physics and cosmology. Discover novel analytic formulas and improve model interpretability.
Deep Learning for Search and Recommender Systems in Practice
Explore deep learning techniques for search and recommendation systems, covering document retrieval, ranking, personalization, and evaluation metrics. Learn about pointwise, pairwise, and listwise ranking approaches.
Deep Learning for Search and Recommender Systems in Practice - Part 2
Explore advanced techniques in deep learning for search and recommender systems, focusing on practical implementation and real-world applications at LinkedIn.
Deep Learning for Search and Recommender Systems in Practice - Part 1
Explore practical applications of deep learning in search and recommender systems, focusing on query understanding, candidate retrieval, and ranking techniques.
Graph Mining Hamilton
Learn graph representation techniques for node classification, link prediction, and graph classification. Explore deep learning on graphs, GNNs, and their applications in drug repurposing and recommender systems.