Common Pitfalls in Computer Vision Project
Uncover and overcome common mistakes in transfer learning for computer vision, with insights into CNN behavior and practical solutions for more effective implementations.
When to Use Machine Learning - Tips, Tricks and Warnings
Discover when and how to effectively apply machine learning, with practical tips and real-world examples from open-source projects and cryptocurrency trading.
Building a Powerful Pet Detector in Notebooks
Learn to build and deploy an AI-powered pet breed detector using Azure Notebooks, TensorFlow, and transfer learning techniques. Optimize the model for improved accuracy and create a web service.
Classification Based on Missing Features in Deep Convolutional Neural Networks
Explore a novel approach to enhance neural network accuracy and robustness in adversarial situations, focusing on classification based on missing features in deep convolutional models.
Audio Classification with Machine Learning
Learn to build practical machine learning models for audio classification using spectrograms, CNNs, and techniques like transfer learning and data augmentation with Keras and TensorFlow.
Getting Started with Apple ML
Introduction to Apple ML: Learn to integrate machine learning into iOS apps using Create ML and Swift, with no math background required. Explore datasets, compare tools, and discover ML possibilities.
A Day in the Life of a Data Scientist - Conquer ML Lifecycle on Kubernetes
Explore a data scientist's daily workflow, from data prep to model deployment, using Kubeflow and Kubernetes for efficient machine learning lifecycle management.
Deep Learning in the World of Little Ponies
Explore computer vision and image classification using deep learning techniques to identify "My Little Pony" characters, with hands-on examples in Keras and Python.
Deep Learning in the World of Little Ponies
Explore computer vision and deep neural networks to build custom image classifiers, with a fun twist using "My Little Pony" characters as examples.
ML BuzzWords Demystified
Demystifies latest ML trends like Reinforcement Learning, AutoML, and ML bias. Provides clear insights into complex concepts, ensuring you're up-to-date with the field's advancements.
Deep Learning in the World of Little Ponies
Explore computer vision and deep learning techniques to build custom image classifiers, using "My Little Pony" characters as an engaging example for practical application.
Pytorch Neural Style Transfer Tutorial
Learn to implement Neural Style Transfer from scratch in PyTorch, covering theory and practical coding to blend content and style images for artistic results.
Layer Increasing Network Scaling (LiNeS) - Preventing Catastrophic Forgetting in Language Models
Explore LiNeS, a novel post-training layer scaling technique that prevents catastrophic forgetting in large language models while enhancing multi-task performance and model merging capabilities.
SETFIT Few-Shot Learning for SBERT Text Classification - Part 43
Discover how SETFIT's few-shot learning approach revolutionizes text classification, outperforming GPT-3 while using SBERT Sentence Transformers for efficient processing with limited training data.
Understanding Robotics Transformer 2 (RT-2) - A Deep Dive into DeepMind's Vision-Language-Action Model
Explore DeepMind's RT2 model and discover how it bridges language models with robotics to enable intelligent reasoning and action in autonomous systems.
Cross-modal Transfer Between Vision and Language for Protest Detection
Explore cross-modal transfer for protest detection using vision and language data. Learn how to leverage pretrained models for zero-shot event detection across different modalities.
Navigating Through the Generative AI Landscape
Explore the latest trends in Generative AI, gaining practical insights for startups to leverage advancements and enhance products in this dynamic field.
Fine-Tuning ViT Classifier with Custom Data - Inference for Images and Videos
Fine-tune a ViT model with custom data and perform inference on images and videos. Learn practical techniques for image and video classification using advanced machine learning.
Technical Shortcomings of Deep Learning - Part 1
Explore technical challenges in deep learning, including data hunger, limited transfer capacity, open-ended inference, and explainability. Gain insights from Gary Marcus's critical appraisal.
RouteLLM - Learning to Route Large Language Models with Preference Data
Optimize LLM deployment with dynamic routing, balancing cost and performance. Learn to train routers using preference data, achieving significant cost reduction while maintaining quality responses.
Analyzing and Exposing Vulnerabilities in Language Models - Session 131
Delve into advanced research on language model vulnerabilities, exploring novel adversarial attack methods and gender bias analysis while discovering practical approaches to enhance AI trustworthiness and fairness.