Productionizing Deep Learning Models at Scale
Explore emerging patterns and best practices for deploying machine learning and deep learning models in production environments at scale.
Federated Learning in Production: Enabling AI Training with Data Privacy
Explore federated learning's applications, benefits, and implementation requirements for AI training on edge devices with data privacy.
Neural ODEs: Continuous-Time Models for Machine Learning - TMLS 2019
Explore neural networks as implicit models and their applications in scientific computing with David Duvenaud at TMLS2019.
Canada's Unique Advantage: AI and Healthcare Landscape
Explore Canada's AI and healthcare landscape, focusing on its unique advantages in data, research, and startups. Discover how AI drives innovation in the healthcare sector.
Risk - The Toughest Barrier to Autonomous Cars
Explore the unexpected challenges in commercializing self-driving technology, focusing on mindset and legal hurdles rather than technical aspects.
Moore's Law is Dead - Now What? The Future of AI Processing
Explore the future of AI processing beyond traditional CPUs and GPUs, focusing on innovative architectures designed for demanding ML workloads in retail and beyond.
Improving Sales Efficiency via Yelp's Model Platform
Enhance sales productivity using machine learning techniques and operationalize models with Yelp's platform. Gain insights from a real-world case study.
Analyzing the Security of Machine Learning for Algorithmic Trading
Explore adversarial attacks on ML-based algorithmic trading systems, evaluating robustness and discussing realistic attack scenarios in financial markets.
Designing a Real-Time Model to Prevent Fake Account Sign-Up
Develop a real-time machine learning service to prevent fake account sign-ups. Learn about statistical challenges, computational scaling, and deployment pitfalls in low-latency ML inference.
How Your ML Model Will Fail - And How to Prepare For It
Explore ML model failure modes, analyze production performance, and set up pragmatic monitoring strategies to prevent degradation and breakage in production.
Responsible AI: Challenges and Emerging Practices - Keynote
Explore challenges and emerging practices in responsible AI, including unintended consequences, model interpretability, fairness, and engineering objectives.
Utterance Generator Fast Tracks Chatbot Training
Explore an utterance generator tool for efficient chatbot training, enhancing natural language understanding and streamlining development processes.
Deep Learning for Program Repair
Explore Google's ML4SE research on training deep learning models to fix software build errors, enhancing developer productivity and reducing project delays.
PolypharmDB: Quickly Identifying Repurposed Drug Candidates for COVID-19
Explore PolypharmDB, a deep learning-based resource for identifying repurposed drug candidates for COVID-19. Learn about accelerated drug discovery methods using existing clinical data.
Machine Learning with Sensitive Data: Privacy-Preserving Techniques
Explore open-source ML techniques for sensitive data in finance and healthcare, ensuring privacy while maximizing data utility.
TinyML and Efficient Deep Learning Computing - Course Summary
Explore efficient machine learning techniques for deploying neural networks on resource-constrained devices, covering model compression, pruning, quantization, and more.
TinyML and Efficient Deep Learning Computing - Lecture 24: Course Summary
Explore efficient machine learning techniques for deploying neural networks on resource-constrained devices. Gain hands-on experience with mobile AI and quantum machine learning.
StreamingLLM: Deploying Language Models for Streaming Applications with Long Text Sequences
Explore innovative techniques for deploying LLMs in streaming applications, focusing on the "attention sink" phenomenon and efficient KV cache management.
TorchSparse++ - Efficient Training and Inference Framework for Sparse Convolution on GPUs
Explore efficient GPU-based sparse convolution with TorchSparse++, an advanced framework for training and inference in deep learning applications.
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Explore activation-aware weight quantization for compressing and accelerating large language models. Learn about AWQ's innovative approach to LLM optimization.
Atomique: A Quantum Compiler for Reconfigurable Neutral Atom Arrays
Explore Atomique, a novel quantum compiler for reconfigurable neutral atom arrays, enhancing scalability and efficiency in quantum computing through strategic atom movements and optimized gate scheduling.