Exploring Techniques to Build Efficient and Robust TinyML Deployments
Explore techniques for efficient TinyML deployments, covering data challenges, quantization, and handling out-of-distribution data for robust edge AI applications.
Getting Started with Caffe - Deep Learning Framework Introduction - Class 3
Learn to define, train, and deploy Deep Neural Networks using Caffe framework. Covers data management, network definition, training monitoring, and deployment for classification or feature extraction.
Scala and Spark in the New Deep Learning Era
Explore integrating large language models into big data infrastructures using Apache Spark, Scala, and BigDL. Learn distributed fine-tuning for pre-trained models and their representation as Spark estimators.
No Data? No Problem: Zero-Data Model Training with Foundational Models
Explore zero-data model training using foundational models to create task-specific models without new data. Learn techniques for leveraging open-source tools in your projects.
AI is MagIA: Explaining AI Concepts with Card Tricks
Unravel AI mysteries through captivating card tricks. Explore data domains, GANs, biased opinions, and transfer learning in this unique blend of magic and technology. Entertaining and informative for all ages.
LLMOps: Fine-Tuning Video Classifier (ViViT) with Custom Data
Fine-tune a Video Vision Transformer (ViViT) using custom datasets. Learn to adapt Google's pretrained model for specialized video classification tasks.
Microsoft AI: ML.NET Framework in C# - Transfer Learning for Image Classification
Aprende a entrenar modelos de aprendizaje profundo personalizados utilizando transferencia de aprendizaje, TensorFlow y ML.NET para clasificar imágenes de superficies de concreto.
Divide and Conquer: Carving Out Symbolic Models from BlackBox for More Efficient Domain Adaptation
Explore techniques for extracting symbolic models from black-box systems, enhancing domain adaptation efficiency in computational genomics and medical imaging.
Train a Production-Level Image Classifier
Learn to build a robust image classifier using advanced techniques like data augmentation, transfer learning, and learning rate scheduling.
Towards Foundation Models for Knowledge Graph Reasoning
Explore ULTRA, a novel approach for universal and transferable graph representations in knowledge graph reasoning, enabling zero-shot inductive inference and fine-tuning on unseen graphs.
Deep Active Learning: Enhancing Data Efficiency in Machine Learning - Lecture
Explore deep learning's data efficiency, active learning in NLP, and innovative approaches to enhance learning from human interactions in AI systems.
Multilingual Speech to Speech Translation for Under-Resourced Languages
Explore cutting-edge AI techniques for seamless multilingual communication, focusing on under-resourced languages through multi-modal and transfer learning approaches.
Static Detection of Novel Malware Using Transfer Learning with Deep Neural Networks
Explore innovative malware detection techniques using transfer learning and deep neural networks for enhanced cybersecurity and threat prevention.
Transfer Learning - Analyst-Sourcing Behavioral Classification
Explore advanced threat detection using AI and transfer learning techniques. Learn about active learning, data sharing, and improving phishing domain detection across organizations.
Transfer Learning - Repurposing ML Algorithms from Different Domains to Cloud Defense
Explore innovative ML applications in cybersecurity through transfer learning, leveraging algorithms from other domains to enhance cloud defense and tackle emerging threats.
Your Voice is My Passport
Explore machine learning's impact on voice authentication security, including synthetic audio generation and potential vulnerabilities in financial and home automation systems.
Audio Classification with Machine Learning
Learn practical techniques for audio classification using machine learning, including spectrograms, CNNs, and transfer learning. Explore applications in speech, music, medical diagnostics, and more using Keras and TensorFlow.
Tensorflow and Deep Learning - Without a PhD
Comprehensive introduction to TensorFlow and deep learning, covering neural networks, convolutional networks, regularization techniques, and practical applications in image and language processing.
Improving Unicode Attacks With Deep Learning
Exploración de ataques Unicode mejorados con aprendizaje profundo, creando un diccionario de caracteres confundibles para desarrollar herramientas ofensivas sofisticadas y nuevos procedimientos de prueba de aplicaciones.
Cross-Dataset Time Series Anomaly Detection for Cloud Systems
Innovative approach combining transfer and active learning for detecting anomalies in cloud systems using limited labeled data, improving efficiency in maintaining service availability.
Best Practices for Real-time Intelligent Video Analytics
Explore best practices for real-time intelligent video analytics, including transfer learning, data augmentation, and NVIDIA tools for efficient AI applications and high-performance inference.