From Idea to Impact, the Crypto Story - What's Next?
Explore the intersection of cryptography and machine learning, examining challenges, impacts, and future directions in digital privacy, adversarial learning, and quantum resilience.
CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
Explore GPU-accelerated privacy-preserving machine learning techniques for enhanced performance and scalability in image classification and private training.
Understanding and Visualizing ResNets That Forever Revolutionized Deep Learning - What Is ResNet
Explore the revolutionary ResNet architecture, its impact on deep learning, and hands-on image classification. Learn about CNN limitations and how ResNet's skip connections transformed the field.
OpenAI's CLIP for Zero Shot Image Classification
Explore OpenAI's CLIP model for flexible computer vision classification without retraining, enabling generalization to new classes and images beyond initial training data.
Bag of Visual Words for Image Classification and Retrieval
Learn to build image embeddings using the Bag of Visual Words technique for image retrieval, object detection, and classification in computer vision applications.
Adversarial Examples in Machine Learning - Crafting and Defending Against Attacks
Explore machine learning vulnerabilities, adversarial examples, and their impact on system security. Learn crafting techniques and defenses through practical tutorials and real-world applications.
Self-Training With Noisy Student Improves ImageNet Classification - Paper Explained
Explore a novel semi-supervised learning approach for image classification using unlabeled data, improving model performance and robustness through iterative self-training and noise injection techniques.
Learning to Classify Images Without Labels - Paper Explained
Explore innovative techniques for unsupervised image classification, combining representation learning, clustering, and self-labeling to group visually similar images without predefined labels.
Supervised Contrastive Learning
Explore a novel supervised learning approach that outperforms cross-entropy loss, improving image classification models' performance and robustness across various architectures and data augmentations.
Weight Standardization
Explores Weight Standardization technique for neural networks, improving performance in micro-batch training and outperforming other normalization methods when combined with Group Normalization.
From Network Dissection to Policy Dissection - Emergent Concepts in Deep Representations
Explore emergent concepts in deep neural networks, from image classification to reinforcement learning, revealing inner workings and enabling meaningful human-AI interactions for content creation and robotics control.
Efficient Tensor Representation for Deep Learning with TensorLy and PyTorch
Explore tensor methods for deep learning, improving performance, speed, and robustness. Learn practical implementation using TensorLy-Torch for video and image classification tasks.
Production Machine Learning Monitoring- Principles, Patterns and Techniques
Practical deep dive on production monitoring of machine learning models, covering standard techniques and advanced paradigms like concept drift, outlier detection, and explainability, with hands-on examples and architectural patterns.
Transfer Learning Using Keras
Learn to classify car brands using transfer learning with Keras and ResNet50. Hands-on tutorial covers dataset preparation, model configuration, training, and prediction visualization.
Transfer Learn in Weather Images
Learn to classify weather images using transfer learning with Python, TensorFlow, and VGG19. Covers dataset preparation, model implementation, and image prediction.
Cancer Detection in Brain Using Deep Learning
Learn to detect brain tumors using deep learning, CNN, and TensorFlow. Build, train, and test a model for classifying brain images with hands-on coding and practical implementation.
How to Classify Flowers Using Deep Learning
Learn to build a convolutional neural network for flower image classification using TensorFlow and Keras, from dataset preparation to model testing and prediction.
TensorFlow Models Accelerated for NVIDIA Jetson
Accelerate TensorFlow models on NVIDIA Jetson: optimize training, integrate TensorFlow RT, enhance image classification, and format models for improved performance.
Attacking Optical Flow
Explores adversarial patch attacks on optical flow networks, revealing vulnerabilities in deep learning-based motion estimation crucial for autonomous driving safety.
NVIDIA Deep Learning: Getting Started with DIGITS - Class 2
Learn to create, test, and optimize deep neural networks using NVIDIA's DIGITS tool for image classification tasks, with hands-on examples and practical deployment strategies.
Powering the Next Generation of IoT with Embedded Machine Learning
Unlock IoT potential with Edge Impulse machine learning and Nordic's low-power wireless solutions. Learn to create motion detection, sound recognition, and image classification on edge devices using nRF52840 and nRF5340 kits.