Self-Supervision & Contrastive Frameworks - A Vision-Based Review
Comprehensive review of self-supervised and contrastive learning frameworks in computer vision, exploring methodologies, performance, and potential applications in medical imaging.
SleepFM - Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
Explore SleepFM, a groundbreaking multi-modal foundation model for sleep analysis, leveraging brain, cardiac, and respiratory data to improve sleep stage classification and disorder detection.
Robust Pre-Training by Adversarial Contrastive Learning - CAP6412 Spring 2021
Explore robust pre-training techniques using adversarial contrastive learning, focusing on unsupervised and semi-supervised methods for improved model resilience and accuracy.
Adversarial Self-Supervised Contrastive Learning
Explore adversarial self-supervised contrastive learning, covering transformers, frameworks, algorithms, evaluations, and experiments in this comprehensive presentation.
Contrastive Learning with Adversarial Examples - Spring 2021
Explore contrastive learning with adversarial examples, covering unsupervised embedding, self-supervised learning, experiments, and architectural studies in this comprehensive overview.
Human Activity Recognition - Learning with Less Labels and Privacy Preservation
Learn advanced techniques for human activity recognition with limited labeled data and privacy preservation, including pseudoleveling, contrastive learning, and zero-shot approaches.
Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph Completion
Explore innovative techniques for enhancing multimodal knowledge graph completion through semantic neighbor retrieval and contrastive learning.
Disentangled Contrastive Hypergraph Learning for Next POI Recommendation - Lecture 4
Explore innovative hypergraph learning techniques for next POI recommendations, enhancing user experience in location-based services.
Building a Multimodal LLM-Based Search Assistant Chatbot for Housing Search - Haystack EU 2024
Explore the development of a multimodal LLM-based chatbot for enhanced housing search, featuring contrastive vision-language models and innovative AI technologies to streamline user experiences in real estate.
Learning from Simulations - Marc Huertas Company
Explore astrostatistics and machine learning in galaxy formation, comparing models with observations and discussing innovative data analysis techniques for advancing astrophysical understanding.
Linear Causal Representations from Interventions under General Nonlinear Mixing
Explore causal representation learning from latent interventions in nonlinear settings. Uncover geometric structures, analyze precision matrices, and evaluate a contrastive algorithm for identifying latent variables.
Large Language Molecular Representation and Learning
Explore molecular machine learning's potential in drug discovery, focusing on representation challenges, self-supervised learning, and leveraging pre-trained language models for property prediction.
Introduction to Machine Learning Model Explanations and Interpretability
Explore key concepts in data science explanations, from gradient-based highlighting to contrastive editing, covering essential techniques for understanding and interpreting complex models.
SETFIT Hyperparameter Optimization for SBERT Text Classification - Part 45
Master SETFIT hyperparameter optimization techniques for efficient text classification using Sentence Transformers, focusing on contrastive training and automated parameter tuning for optimal performance.
SetFit with SBERT for Few-Shot Text Classification - Multi-Class and Multi-Label
Master SetFit and SBERT techniques for efficient few-shot text classification, exploring contrastive training, dense embeddings, and classification head implementation for both multi-class and multi-label scenarios.
OpenAI CLIP - Connecting Text and Images - Paper Explained
Explore OpenAI's CLIP model for connecting text and images, covering its methodology, zero-shot capabilities, and performance comparisons. Learn about its embedding space quality and limitations.
How to Represent Part-Whole Hierarchies in a Neural Network - Geoff Hinton's Paper Explained
Explore GLOM, a novel computer vision model combining transformers, neural fields, and capsule networks to dynamically construct parse trees for object recognition and scene understanding.
Toward Generalizable Embodied AI for Machine Autonomy
Explore recent advancements in machine autonomy, focusing on generalizable embodied AI through sequential decision-making, simulation environments, and human-AI collaboration.
CMU Advanced NLP: Pre-training Methods
Explore advanced NLP concepts including multi-task learning, sentence embeddings, BERT variants, and language modeling objectives. Gain insights into cutting-edge techniques for natural language processing.
CURL - Contrastive Unsupervised Representations for Reinforcement Learning
Explore how contrastive learning enhances reinforcement learning, improving performance in complex tasks using high-level features extracted from raw pixels.
Self-Supervised Learning in Computer Vision
Explore self-supervised learning in computer vision, covering pretext tasks, clustering, and contrastive learning. Gain insights into PIRL framework and its evaluation across various applications.