Segment Anything Model (SAM) Explained
Explore SAM, a versatile image segmentation model by Meta AI. Learn about its multitask capabilities, zero-shot transferability, and applications across various scenes and objects.
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Explore OpenMoE, an open-source Mixture-of-Experts language model series. Discover its cost-effectiveness, routing mechanisms, and key insights in comparison to dense LLMs.
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Explore LayerSkip, an LLM acceleration method that speeds up inference by strategically restricting model layers, achieving 2x speed-ups on various tasks through innovative techniques.
Towards Monosemanticity: Decomposing Language Models with Dictionary Learning
Explore monosemanticity in neural networks through sparse autoencoders. Learn how extracting interpretable features enhances understanding of language model behavior and improves reasoning capabilities.
Knowledge Circuits in Pretrained Transformers Explained
Explore knowledge circuits in pretrained transformers, uncovering computational mechanisms behind language models' articulation of specific knowledge. Gain insights into AI's inner workings.
Connecting Vision and Language End-to-End - 2018
Explore neural models for vision-language understanding, focusing on End-to-End Module Networks and dense video captioning. Learn about interpretable, compositional approaches to visual question answering.
Rich Morphological Modeling for Multi-lingual HLT Applications - 2016
Explore advanced morphological modeling techniques for diverse languages, enhancing HLT applications through innovative approaches like neural networks and cross-lingual projection.
Feature Rich Models for Discourse Signaling - 2018
Explore computational models for discourse relations using rich annotations beyond text, including syntactic and semantic information, to capture complex discourse structures.
Introduction to Artificial Neural Networks - JSALT 2023
Explore artificial neural networks: fundamentals, architectures, and applications in this comprehensive introduction from JSALT 2023 workshop.
Toward Length Extrapolatable Transformers
Explore innovative techniques for enhancing transformer models' ability to handle longer sequences, improving their performance and scalability in natural language processing tasks.
AI and the Impending Revolution in Brain Sciences - 2002
Explore the synergy between AI and brain sciences, examining how AI architectures interpret brain activity data and how machine learning discovers patterns in neurological research.
Emergent Computation and Learning from Assemblies of Neurons
Explore emergent computation and learning in neural assemblies with Dr. Santosh Vempala's insightful seminar on cutting-edge neuroscience research.
Programming with Neural Surrogates of Programs
Explore neural surrogates for program optimization, including case studies on CPU simulators and techniques like the Renamer and Turaco for constructing efficient program surrogates.
Learning and Inference with Prior Knowledge
Explore how prior knowledge influences learning and inference in intelligent systems, from human cognition to AI, with insights on improving behavioral robustness in deep networks.
Опыт применения нейронных сетей для решения геологических задач КФУ
Изучите применение нейронных сетей в геологии, повысьте эффективность решения задач и расширьте профессиональные навыки в этой области.
Применение нейронных сетей при интерпретации геофизических данных - Часть I
Изучите применение нейронных сетей для интерпретации геофизических данных, включая основы и практические аспекты их использования в геофизике.
Learning Operators - Lecture 1
Explore learning operators in scientific machine learning, covering traditional methods, neural networks, and practical applications for mathematical problem-solving.
Finite Neuron Method - Lecture 3
Explore advanced mathematical concepts in finite neuron methods through an in-depth lecture by Jinchao Xu, focusing on theoretical foundations and practical applications.
Finite Neuron Method - Lecture 2
Explore finite neuron method, covering electrical entropy, curse of dimensionality, neural networks, and approximation properties. Gain insights into deep learning concepts and techniques.
Finite Neuron Method - Lecture 1
Explore finite neuron method fundamentals, covering finite element method, neural networks, and adaptive PD. Gain insights into mathematical concepts and their applications.
From Word Prediction to Complex Skills: Compositional Thinking and Metacognition in Large Language Models - Keynote
Explore compositional thinking and metacognition in large language models, from basic word prediction to complex skill development, with Princeton's Sanjeev Arora.