Social Visual Representations in Humans and Machines
Explore neural face representations, disentangled learning, and social interaction perception in vision, examining shared visual representations between humans and machines.
As Simple as Possible, but Not Simpler - Features of the Neural Code for Visual Recognition
Explore visual recognition in the brain through neural coding, feature visualization, and experiments comparing monkey behavior with convolutional neural networks.
Why It Pays to Study Psychology - Lessons from Computer Vision
Explore how psychology insights enhance computer vision, from texture analysis to scene recognition and 3D reasoning. Learn about occlusion, visual memory, and self-supervised learning.
Conversational AI with Transformer Models - Building Blocks and Optimization Techniques
Explore building conversational AI agents using transformer models, covering advantages over RNN/LSTM, knowledge distillation, and model compression techniques for efficient production deployment.
Automated Background Removal Using PyTorch - Wehkamp's Image Processing Pipeline
Discover an automated pipeline for efficient background removal in product images using PyTorch and machine learning, enhancing visual experiences for e-commerce customers.
Practical Adversarial Attack Against Speech Recognition Platforms
Explore techniques for adversarial attacks on speech recognition systems, focusing on Amazon Echo and Kodi. Learn about blackbox approaches and philosophical implications.
Trees and Series-Parallel Graphs - Lecture 22a of CS Theory Toolkit
Explore treewidth, CSPs, and graph theory fundamentals for theoretical computer science research, focusing on trees and series-parallel graphs.
Constraint Satisfaction Problems - Lecture 20b of CS Theory Toolkit
Explore Constraint Satisfaction Problems, their formal definition, examples, and algorithms. Learn about the Dichotomy Theorem and its implications for theoretical computer science research.
Analysis of Boolean Functions at CMU - Constraint Satisfaction Problems
Explore constraint satisfaction problems in boolean functions, covering topics like Max3SAT, Max3Coloring, and approximation algorithms for complex computational challenges.
Security and Trustworthiness of Modern Cyber-Physical Systems - Dr. Dimitrios Damopoulos
Explore challenges and strategies for securing interconnected cyber-physical systems, focusing on machine learning, smartphone security, and AI trustworthiness in our increasingly digital world.
Easy Audio-Reactive Music Videos with Deforum and Automatic1111
Create audio-reactive music videos using Deforum and Automatic1111 webui. Learn to synchronize visuals with audio, install tools, choose prompts, and generate stunning AI-powered animations for your music.
Textual Inversion and Hypernetworks - Stable Diffusion 2
Deep dive into training Hypernetworks and Textual Inversion Embeddings for Stable Diffusion, covering setup, models, and best practices for optimal results, even with limited image data.
RL Foundation Models Are Coming!
Explore DeepMind's AdA algorithm, combining meta-learning, attention, and curriculum learning for advanced reinforcement learning. Discover promising results and future prospects in this emerging field.
LangChain Data Loaders, Tokenizers, Chunking, and Datasets - Data Prep
Learn to prepare text data for LLMs using LangChain tools: data loading, tokenization, chunking, and dataset creation. Practical guide for efficient text processing in AI applications.
Convolutional Neural Networks
Explore convolutional neural networks for computer vision, covering feature extraction, convolution operations, and applications like object detection and self-driving cars.
ChatGPT Plugins - Build Your Own in Python
Learn to build ChatGPT plugins in Python using OpenAI's template. Covers setup, deployment, and integration with ChatGPT, focusing on a retrieval plugin for LangChain documentation.
DALL-E 3 Will Be the Best AI Art Generator We've Ever Seen
Explore DALL-E 3's advanced AI image generation capabilities, including improved accuracy, photorealism, prompt interpretation, and diverse artistic styles integrated with ChatGPT.
Let's Build an AI Voice Assisted Using ChatGPT API - ChatGPT API Tutorial - Generative AI Series
Build an AI voice assistant using ChatGPT API, exploring generative AI capabilities and integrating voice technology for interactive and intelligent conversational experiences.
Perception and Collaboration in Robotics - Session 18
Explore cutting-edge research on perception and collaboration in robotics and AI, focusing on advancements in sensing, decision-making, and multi-agent systems.
Tracking Techniques in Computer Vision - Session 25
Explore advanced tracking techniques and algorithms for object detection and motion analysis in computer vision applications.
Digging Into Container Image Layers for Sneaky Vulnerabilities
Explore techniques to identify and mitigate hidden vulnerabilities in container image layers, focusing on Java-based images and using tools like Trivy and dive for in-depth analysis.