Contrastive Hierarchical Clustering
Explore Contrastive Hierarchical Clustering techniques and applications in this insightful conference talk by Przemysław Rola from the University of Economics in Krakow.
Deep Statistical Solvers and Power Systems Applications
Explore deep learning applications in power systems, focusing on Graph Neural Networks to address topological changes and optimize grid operations through unsupervised learning.
Global Optimization for Cardinality-Constrained Minimum Sum-of-Squares Clustering via Semidefinite Programming
Explore global optimization techniques for cardinality-constrained minimum sum-of-squares clustering using semidefinite programming, focusing on exact algorithms and state-of-the-art approaches.
Введение в машинное обучение - Часть V
Изучите основы машинного обучения, включая ключевые концепции и методы, для развития навыков в этой перспективной области информационных технологий.
Artificial Intelligence per Kilowatt-Hour - Max Welling, University of Amsterdam
Explore cutting-edge AI efficiency: compressing neural nets, low-precision computing, and spiking networks to maximize intelligence per kilowatt-hour as AI moves to edge devices.
Targeting Crimes and Criminals Through Data - Dr. Rick Adderley
Explore data mining in law enforcement, covering challenges in police data analysis, criminal network analysis, and advanced analytics for crime prevention and resource optimization.
Malware Clustering - Static and Dynamic Behavior Analysis
Explore innovative malware clustering techniques using static and dynamic behavior analysis, machine learning, and similarity search for robust, scalable, and repeatable results.
New Twists for New Tricks - Making Audio Deep Learning Practical
Explore innovative approaches to audio deep learning, addressing practical challenges in efficiency, unsupervised learning, and resource-limited scenarios for enhanced audio processing and source separation.
Building Adaptable Generalist Robots
Explore cutting-edge approaches for building adaptable generalist robots, focusing on in-context learning, unsupervised reinforcement learning, and leveraging foundation models for improved generalization and task versatility.
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Explores challenges in unsupervised learning of disentangled representations, questioning assumptions and efficacy of current approaches through theoretical analysis and extensive experiments.
Data Science + Design Thinking - Perfect Blend to Achieve the Best User Experience - Michael Radwin
Blend data science with design thinking to create AI/ML products that prioritize customer needs, using empathy, experimentation, and rapid prototyping for optimal user experience.
Gael Varoquaux at ODSC Boston 2015 - Scikit-Learn for Easy Machine Learning
Explore machine learning with scikit-learn: its popularity, capabilities, and future. Learn about easy predictive analysis, development process, and exciting new features in this data science ecosystem.
A Review of Machine Learning Techniques for Anomaly Detection - Dr. David Green
Explore machine learning techniques for anomaly detection, covering traditional methods, deep neural networks, and practical applications in various domains.
Unsupervised Discovery of Temporal Sequences in High-Dimensional Datasets
Explore unsupervised discovery of temporal sequences in high-dimensional datasets using seqNMF, a tool extending convolutional NMF. Learn to extract and validate neural sequences from large-scale recordings.
Unsupervised Features Learning for Sampled Vector Fields
Explore innovative techniques for analyzing sampled vector fields using graph structures and unsupervised learning, revealing hidden features correlated with known dynamics in analytical models.
At Scale Anomaly Detection for Enterprise Security - Joshua Neil, Microsoft
Explore scalable anomaly detection for enterprise cybersecurity with Microsoft's Joshua Neil. Learn about real-time telemetry, unsupervised learning, and post-breach detection techniques.
Geometric Graph-Based Methods for High Dimensional Data
Explore geometric graph-based methods for segmenting large datasets, combining nonlinear PDE image segmentation with linear algebra techniques to solve graph cut optimization problems in various applications.
Automated Pipeline for Large-Scale Neural Network Training and Inference
Explore cloud-native ML pipeline for automated anomaly detection using BiLSTM models. Learn to manage thousands of models with data collection, training, validation, and deployment techniques.
Smoothed Analysis for Tensor Decompositions and Unsupervised Learning
Explore smoothed analysis for tensor decompositions and unsupervised learning, focusing on polynomial time guarantees and robust decompositions of symmetric overcomplete tensors.
Tensor Decompositions - A Quick Tour of Illustrative Applications
Explore tensor decompositions for data analysis and dimensionality reduction. Learn fundamentals, applications in various fields, and hands-on examples using real-world datasets.
Unsupervised Alignment of Graphs and Embeddings: Fundamental Limits and Computational Methods
Explore unsupervised alignment techniques for graphs and embeddings, examining fundamental limits and computational approaches for data analysis and machine learning applications.