
Explore deep learning applications, from basic concepts to advanced techniques. Learn about neural networks, optimization methods, and real-world uses in image and speech recognition.

Explore connections between information theory, statistical physics, and learning. Delve into classical statistics, high-dimensional problems, and Bayesian approaches, with applications in signal processing and regression.

Explore advanced perturbation techniques for nonlinear PDEs, focusing on multiple scales, asymptotic analysis, and the interplay between linear waves and nonlinearity in various scientific contexts.

Explore perturbation methods for nonlinear PDEs, focusing on shallow water waves and damped KDV models. Learn unified approaches to adapt linear equation techniques to nonlinear contexts.

Explore perturbation methods for nonlinear PDEs, focusing on nonlinear oscillators and periodic solutions. Learn techniques like inner products, perturbation series, and 2Pi periodicity to tackle complex equations.

Explore perturbation methods for nonlinear PDEs, focusing on adapting linear equation techniques. Learn unified approaches through examples from cold atoms, water waves, and atmospheric science.

Explores untrained neural networks as image models, focusing on the Deep Decoder for efficient compression and denoising. Discusses theoretical foundations and compares performance to other approaches.

Explore deep reinforcement learning for marked temporal point processes, covering event representation, policy optimization, and applications in information propagation and knowledge creation.

Explore machine learning applications at Amazon, from product recommendations to size prediction, with insights on challenges and innovative approaches in e-commerce AI.

Explore ProtoDash, a fast interpretable prototype selection method for extracting compact representations of large datasets, with applications in causal reasoning, data relationships, and prediction accuracy improvement.

Explores a deep generative model for molecular graphs using variational autoencoders, discussing its design, properties, and applications in drug discovery and molecule optimization.

Explores inverse problems using generative priors, comparing to sparsity models. Covers theory, algorithms, and applications in compressive sensing and phase retrieval, with focus on deep learning approaches.

Explores theoretical aspects of deep learning, including overparameterization, optimization, generalization, and generative models, offering insights for researchers and practitioners in machine learning.

Comprehensive introduction to machine learning fundamentals, covering mathematical formalization, deep learning concepts, optimization techniques, and real-world applications in various domains.

Comprehensive introduction to quantum computation, covering key concepts like quantum parallelism, annealing, gates, and qubits. Explores various quantum computer types and fundamental operations in quantum mechanics.

Explore efficient invariant embeddings for universal equivariant learning, focusing on group symmetries in machine learning tasks and their applications in various architectures like CNNs and graph neural networks.

Explore molecular dynamics simulations and machine learning techniques to analyze interfacial hydrophobicity, focusing on efficient data analysis methods and topological approaches for complex chemical systems.

Explore deep learning's interaction with Topological Data Analysis, focusing on explainability and performance enhancement in neural networks and various data analysis applications.

Explore adaptive sampling for Delaunay triangulations of Riemannian manifolds, focusing on curvature variation and quality bounds for successful triangulation. Learn about geometric realizations and manifold triangulation techniques.

Explore robust regression techniques for learning and estimation in algorithms and optimization, focusing on practical applications and theoretical foundations.

Explore efficient methods for escaping saddle points in non-convex optimization, focusing on perturbed gradient descent and its applications in various algorithmic settings.