Classical and Deep Learning Approaches to Longitudinal Modeling in Neuroimages - CGSI 2024
Explore classical and deep learning methods for longitudinal modeling in neuroimaging, focusing on disease progression analysis and innovative techniques for tracking brain changes over time.
Lightweight Deep Learning on Edge Devices - Energy Efficient Approaches
Discover efficient deep learning techniques for edge devices, focusing on energy-saving approximation methods that maintain accuracy while improving performance on smartphones and IoT devices.
Expert API LLM Gorilla-7B: Writing Code for APIs Using Large Language Models
Discover how Gorilla-7B, an API-optimized language model, generates complete code sequences from natural language prompts for tasks like image recognition and language translation.
Python Classes for AI Model Subclassing and Fine-tuning
Master Python classes and their application in AI development, focusing on LLM fine-tuning and Vision transformer implementation with KERAS3 functionality.
Benchmarking Storage with AI Workloads - Performance Analysis and Optimization
Explore how storage systems impact AI/ML workload performance through comprehensive benchmarking analysis, focusing on data ingestion, training patterns, and inference workload optimization.
SaFeR: A Safety Framework for e-Scooter Riders
Explore a comprehensive safety framework for e-scooter riders, featuring real-time monitoring systems, deep learning algorithms, and adaptive safety metrics for enhanced urban micromobility.
Getting the Best of Both Worlds - IoT and Edge Using Hierarchical Inference
Explore hierarchical inference strategies for optimizing IoT and edge computing, focusing on machine fault detection and image classification while balancing accuracy with resource constraints.
AI on the Edge with Eclipse Kura - From Data Collection to Model Deployment
Discover how to build and deploy machine learning applications on edge devices using Eclipse Kura, from data collection through Kura Wires to model training and inference with Nvidia Triton Server.
Predicting Diabetes with Logistic Regression in TensorFlow.js - Deep Learning for JavaScript Hackers
Learn to build and train logistic regression models in TensorFlow.js for diabetes prediction. Covers data visualization, dataset creation, model evaluation, and advanced techniques.
Knowledge Graphs for the Greater Good - ODSC Europe 2020
Explore knowledge graphs' potential in enhancing machine learning, tackling misinformation, and addressing global challenges like climate change and COVID-19 through semantic web principles and real-world applications.
From Python to PySpark and Back Again - Unifying Single-Host and Distributed Deep Learning with Maggy
Unifying single-host and distributed deep learning with Maggy framework, enabling seamless transition from laptop to cluster for efficient model development and training using TensorFlow and PySpark.
Deep Learning in MATLAB: From Algorithm Design to Embedded Deployment on NVIDIA Jetson
Explore deep learning in MATLAB, from transfer learning to GPU deployment on NVIDIA Jetson. Learn algorithm design, CUDA compilation, and performance optimization for embedded systems.
Develop and Deploy Deep Learning Services at the Edge with IBM and NVIDIA Jetson
Explore deploying deep learning services at the edge using NVIDIA Jetson and IBM technologies, covering setup, development, and practical applications in machine learning and AI.
Deep Learning with the Analytical Engine
Explore the potential of the Analytical Engine for deep learning, blending 19th-century mechanical computing with modern AI concepts in this Victorian-era adventure.
Creating Python Gradio UI for Stable Diffusion Models - Part 2
Learn to create a Python Gradio UI for Stable Diffusion models, covering UI design, prompt validation, tab creation, and integration of various functionalities in this hands-on coding tutorial.
Data Processing Fundamentals - Create GUI for Data Application with Gradio
Learn to create a GUI for data applications using Gradio, covering combined interfaces, tabbed layouts, validation, and integrating filters for enhanced data processing and visualization.
Accelerating Research with Microsoft Azure - Dr. Kenji Takeda, Microsoft
Explore cloud computing with Azure for faster, reproducible data science research. Hands-on labs cover deep learning, NLP, ML deployment, and more across various scientific disciplines.
Improvements to NVIDIA CUDA and Deep Learning Libraries - Session 1
Explore NVIDIA's latest AI tech advancements, including CUDA Graphs, WMMA, and cuDNN. Learn about performance improvements, Tensor Cores, and new features for deep learning acceleration.
TinyML Talks - Demoing the World’s Fastest Inference Engine for Arm Cortex-M
Explore the world's fastest inference engine for Arm Cortex-M microcontrollers, featuring live demonstrations, benchmarks, and insights into achieving superior speed and memory efficiency.
Autonomous Nano-UAVs: An Extreme Edge Computing Case
Exploring autonomous nano-UAVs as extreme edge computing cases, focusing on onboard intelligence, machine learning techniques, and full-stack solutions for navigation and human-robot interaction in resource-constrained environments.
Building a React Stable Diffusion App in 15 Minutes
Build a React app for Stable Diffusion image generation in 15 minutes, combining Python and JavaScript. Includes code, deployment tips, and a challenge to improve upon the previous UI.