Collective Intelligence for Deep Learning - A Survey of Recent Developments
Survey of recent developments in collective intelligence for deep learning, exploring self-organization, emergent behavior, and cellular systems to address robustness and adaptability issues in neural networks.
Physical Computation in Insect Swarms - IPAM at UCLA
Explore physical computation in insect swarms, focusing on firefly visual signals and bee pheromone communication. Discover how swarm intelligence emerges from individual interactions.
Multi-Agent Common Sense - IPAM at UCLA
Explore multi-agent common sense through mathematical frameworks combining Bayesian learning and game theory. Discover insights into human collaboration, joint intentions, and cultural knowledge acquisition.
Towards Assurance-Based Learning-Enabled Cyber-Physical Systems
Exploring formal verification, monitoring, and safety case formalization for assurance-based learning-enabled cyber-physical systems, focusing on autonomous vehicles and their complex components.
Bridging the Gap Between Safety and Real-Time Performance for Autonomous Vehicle Control
Explores a novel trajectory planning method for autonomous vehicles, balancing safety and real-time performance through offline computations and runtime optimization to ensure persistent feasibility.
Perception and Learning for Autonomous Driving - Part 1
Explore perception and learning for autonomous driving, covering sensor suites, deep neural networks, and object detection techniques in this comprehensive tutorial.
On Bayesian Models with Networks for Reconstruction and Detection
Explore Bayesian models with neural networks for MRI reconstruction and outlier detection in medical imaging, focusing on network-based priors and generative modeling approaches.
Geometric Understanding of Supervised and Unsupervised Deep Learning for Biomedical Image Reconstruction
Geometric understanding of deep learning for biomedical image reconstruction, exploring supervised and unsupervised approaches, with applications in various imaging modalities.
Deep Learning-Based MR Image Reconstruction and Contrast Conversion
Explore deep learning techniques for MR image reconstruction, parallel imaging, and contrast conversion, focusing on k-space and image space applications in medical imaging.
Quadratic Forms in Surface Automorphisms and Singularity Theory
Explore pseudo-periodic surface automorphisms, quadratic forms, and their applications in singularity theory. Gain insights into Milnor fibers and monodromy automorphisms.
Spectrum of Singularities
Explore hypersurface singularity spectra: definition, properties, and computational techniques. Learn about Thom-Sebastiani theorem, semicontinuity, and applications in algebraic geometry.
Prompt Engineering for GPT-3.5-Turbo, GPT-4
Explore 16 diverse prompts for OpenAI's GPT models, including document processing and creative applications, with practical Python implementations and code reviews.
Machine Learning and Neural Networks: Activation Functions - Day 11
Explore activation functions in neural networks, their role in machine learning, and how they impact model performance and decision-making processes.
Machine Learning and Neural Networks: Decision Trees - Day 10
Explore decision trees in machine learning and neural networks, covering key concepts and applications for data-driven decision-making.
Machine Learning and Neural Networks: Logistic Regression - Day 6
Explore logistic regression in machine learning and neural networks, covering key concepts and applications for binary classification problems.
Machine Learning and Neural Networks: Simple and Multiple Linear Regression - Day 5
Learn simple and multiple linear regression techniques for machine learning and neural networks, covering key concepts and practical applications.
Training and Testing Data in Machine Learning and Neural Networks - Day 4
Explore training and testing data concepts in machine learning and neural networks, enhancing your understanding of model evaluation and performance optimization.
Machine Learning and Neural Networks: Data Preprocessing Techniques - Day 3
Explore data preprocessing techniques for machine learning: handling missing data, normalization, standardization, and binarization. Enhance your ML and neural network skills.
Deep Learning Applications by Rina Panigrahy
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.
Deep Decoder: Concise Image Representations from Untrained Networks - Lecture 2
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.
Inverse Problems under a Learned Generative Prior - Lecture 1
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.