{"id":6874,"date":"2022-02-14T09:05:54","date_gmt":"2022-02-14T09:05:54","guid":{"rendered":"https:\/\/mead.ch\/mead\/?p=6874"},"modified":"2024-03-07T20:09:45","modified_gmt":"2024-03-07T20:09:45","slug":"hw-accelerated-machine-learning-at-the-edge","status":"publish","type":"post","link":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/","title":{"rendered":"Hardware-Efficient Edge AI"},"content":{"rendered":"

<\/a><\/p>\n

Abstracts<\/a>Practical Information<\/a>Course Material<\/a><\/div>\n

On-Line Class
\nCET – Central European Time Zone<\/span><\/h3>\n

Download One-Page Schedule Here<\/a><\/p>\n\n\n\n
\n

Week 1: March 12-15, 2024<\/h4>\n

Week 2: March 18-22, 2024<\/h4>\n

Registration deadline: February 23, 2024<\/strong><\/span>
\nPayment deadline: March 1, 2024<\/strong>
\n<\/span><\/td>\n

\"registration\"<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n\n\n\n
\n

TEACHING HOURS
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

DAILY<\/td>\nCentral European Time CET<\/strong><\/td>\nEastern Standard Time EST<\/strong><\/td>\nPacific Standard Time PST<\/strong><\/td>\nIndia Standard Time IST<\/strong><\/td>\n<\/tr>\n
Module 1<\/td>\n3:00-4:30 pm<\/td>\n9:00-10:30 am<\/td>\n6:00-7:30 am<\/td>\n7:30-9:00 pm<\/td>\n<\/tr>\n
Module 2<\/td>\n5:00-6:30 pm<\/td>\n11:00 am-12:30 pm<\/td>\n8:00-9:30 am<\/td>\n9:30-11:00 pm<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

WEEK 1: March 12-15
\n<\/strong><\/span><\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Tuesday, March 12
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nContext:<\/strong> ML Applications, Scenario’s and Constraints for the Edge<\/td>\nMarian Verhelst,
\nKU Leuven<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nContext:<\/strong> ML Algorithms and Resulting Challenges<\/td>\nMarian Verhelst,
\nKU Leuven<\/td>\n<\/tr>\n
\n

Wednesday, March 13
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nAlgorithms:<\/strong> Neural Network Compression for the Edge<\/td>\nTijmen Blankevoort, Meta<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nAlgorithms:<\/strong> Neural Network Quantization for the Edge<\/td>\nTijmen Blankevoort, Meta<\/td>\n<\/tr>\n
\n

Thursday, March 14
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nHW, CPU:<\/strong> Specializing Processors for ML<\/td>\nLuca Benini,
\nUni Bologna\/ETHZ<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nHW, CPU:<\/strong> From Single to Multi-Core Low-Power SoCs for ML<\/td>\nLuca Benini,
\nUni Bologna\/ETHZ<\/td>\n<\/tr>\n
\n

Friday, March 15
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nHW, Digital:<\/strong> Concepts Towards ML Acceleration<\/td>\nMarian Verhelst,
\nKU Leuven<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nHW, Digital:<\/strong> Exploiting Quantization and Sparsity at the HW Level<\/td>\nMarian Verhelst,
\nKU Leuven<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

WEEK 2: March 18-22
\n<\/strong><\/span><\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Monday, March 18
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nHW, Analog:<\/strong> Analog\/Mixed-Signal Acceleration<\/td>\nNaveen Verma,
\nPrinceton<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nHW, Tech:<\/strong> Architectural Integration of Emerging Compute Models and Technologies<\/td>\nNaveen Verma,
\nPrinceton<\/td>\n<\/tr>\n
\n

Tuesday, March 19
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nTools:<\/strong> Accelerator Code Generation<\/td>\nTobias Grosser, University of Cambridge<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nTools:<\/strong> Landscape of DL Compilers<\/td>\nTobias Grosser, University of Cambridge<\/td>\n<\/tr>\n
\n

Wednesday, March 20
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nEmerging ML Paradigms:<\/strong> Neuro-Inspired Computing<\/td>\nJan Rabaey,
\nUC Berkeley<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nEmerging ML Paradigms: <\/strong>Towards Cognitive Systems<\/td>\nJan Rabaey,
\nUC Berkeley<\/td>\n<\/tr>\n
\n

Thursday, March 21
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nSystem:<\/strong> Efficient Execution of Approximated AI Algorithms on Heterogeneous Edge AI Systems<\/td>\nDavid Atienza,
\nEPFL<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nUse Cases:<\/strong> Application-Driven System Design and Optimization flow of Edge AI Use Cases in Industrial and Medical Domains<\/td>\nDavid Atienza,
\nEPFL<\/td>\n<\/tr>\n
\n

Friday, March 22
\n<\/strong><\/span><\/h4>\n<\/td>\n<\/tr>\n

3:00-4:30 pm<\/td>\nPractical Use Cases:<\/strong> Energy Efficient ML Applications for Metaverse<\/td>\nHuichu Liu, Meta<\/td>\n<\/tr>\n
5:00-6:30 pm<\/td>\nCross-Layer Optimization<\/td>\nMarian Verhelst,
\nKU Leuven<\/td>\n<\/tr>\n
\"registration\"<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Scroll to Top<\/a><\/p>\n

\n

<\/a><\/p>\n

Abstracts<\/strong><\/span><\/h2>\n

\"registration\"<\/a><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Hardware-Efficient Edge AI
\nOn-Line Class
\n<\/b>March 12-22, 2024
\n<\/b><\/p>\n<\/td>\n<\/tr>\n

\n

Course Abstract
\n<\/b><\/p>\n

Artificial intelligence workloads become more and more important for intelligent edge and extreme-edge devices, a trend also known as “tinyML”. Yet, these workloads come with significant computational complexity, making their execution until recently only feasible on power-hungry server or GPU platforms. Recently a surge of techniques at the algorithmic, hardware architecture and circuit domain are now also creating breakthroughs to enable ML workloads in real-time embedded devices at the edge and extreme edge under low energy and latency budget. Such system optimization, however, does require thorough knowledge and cross-layer optimization across all these fields, all the way from application and algorithm, over compilers and schedulers, to system design, macro-architecture design and circuit design. In this course, we will go over all these aspects of machine learning at the edge, with especially a deeper dive into hardware optimization opportunities. Enough time is also foreseen to discuss practical case studies and end-to-end-optimizations.<\/p>\n<\/td>\n<\/tr>\n

\n

ML Applications, Scenario’s and Constraints for the Edge
\nMarian Ver<\/b>helst, KU Leuven, Belgium
\n<\/b><\/p>\n

– Overview of applications
\n– Cloud vs Edge vs tinyML (extreme edge)
\n– Inference vs learning vs federated learning
\n– Application constraints and scenario’s
\n– Flavors of ML and AI (types of models)<\/p>\n<\/td>\n<\/tr>\n

\n

ML Algorithms and Resulting Challenges
\nMarian Verhelst, KU Leuven, Belgium
\n<\/b><\/p>\n

Computational consequences and HW requirements for the EDGE of:
\n– Probabilistic models
\n– decision trees
\n– SVM’s
\n– NN’s (deep and non-deep; layer types, …)
\n– NN training
\n– Hyperdim computing?
\nChallenges and requirements for efficient AI at the edge.<\/p>\n<\/td>\n<\/tr>\n

\n

Neural Network Compression for the Edge
\nTijmen Blankevoort, Meta, The Netherlands
\n<\/b><\/p>\n

– Take any network, how can we make it smaller structurally?
\n– Neural Network Pruning
\n– Structured Compression
\n– Neural Architecture Search as a compression method.<\/p>\n<\/td>\n<\/tr>\n

\n

Neural Network Quantization for the Edge
\nTijmen Blankevoort, Meta, The Netherlands
\n<\/b><\/p>\n

– Quantization Introduction and Simulation
\n– Quantization-aware training
\n– Post-training quantization techniques
\n– Mixed Precision.<\/p>\n<\/td>\n<\/tr>\n

\n

Specializing Processors for ML
\nLuca Benini, Universit\u00e0 di Bologna, Italy\/ETHZ, Switzerland
\n<\/b><\/p>\n

– Classical instruction set architectures (ISAs) limitations for ML
\n– ISA Extensions for ML
\n– Micro-architecture of ML-specialized cores
\n– PPA (power performance area) optimization and implementation techniques.<\/p>\n<\/td>\n<\/tr>\n

\n

From Single to Multi-Core Low-Power SoCs for ML
\nLuca Benini, Universit\u00e0 di Bologna, Italy\/ETHZ, Switzerland
\n<\/b><\/p>\n

– Single-core ML SoCs – architecture, implementation, PPA analysis
\n– Multi-core ML SoCs – architecture, implementation, PPA analysis
\n– Integration of cores and Hardwired ML accelerators
\n– Memory hierarchy: challenges and solutions.<\/p>\n<\/td>\n<\/tr>\n

\n

Concepts Towards ML Acceleration
\nMarian Verhelst, KU Leuven, Belgium
\n<\/b><\/p>\n

– ML models \/ CNN \/ DNN recap formalization; GeMM
\n– GeMM on traditional CPU \/ GPU
\n– Energy\/latency losses and opportunities
\n– Concepts towards more efficient ML acceleration on single core\/single layer
\n– Parallelization (spatial unrolling optimization)
\n– Stationarity (temporal unrolling optimization)
\n– Extending spatial and temporal unrolling to higher levels.<\/p>\n<\/td>\n<\/tr>\n

\n

Exploiting Quantization and Sparsity at the HW Level
\nMarian Verhelst, KU Leuven, Belgium
\n<\/b><\/p>\n

– Concepts towards more efficient AI acceleration on single core\/single layer (ctu)
\n– Sparse workloads
\n– Quantization – analog domain
\n[Optional: – Concepts towards more efficient AI acceleration on multi-core\/multi-layer].\u00a0<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Analog\/Mixed-Signal Acceleration
\nNaveen Verma, Princeton University, USA
\n<\/b><\/p>\n

– Review of key ops to accelerate (MACs) and potential energy savings through analog
\n– Overview of Approaches for MACs
\n\u2022 Electronic (current, voltage, charge summing)
\n\u2022 Optical
\n– Overheads and limitations
\n\u2022 Memory accessing -> motivates in-memory computing
\n\u2022 Data conversion
\n\u2022 Technology integration with digital engines\/memory
\n– Fundamental tradeoffs
\n\u2022 Energy\/throughput vs SNR
\n– In-memory computing
\n\u2022 Different memory techs and approaches.<\/p>\n<\/td>\n<\/tr>\n

\n

Architectural Integration of Emerging Compute Models and Technologies
\nNaveen Verma, Princeton University, USA
\n<\/b><\/p>\n

– Dataflow bottlenecks (weight\/state loading)
\n– Structured memory accessing and benefits of emerging memory
\n– Co-design with trainers.<\/p>\n<\/td>\n<\/tr>\n

\n

Tools: Accelerator Code Generation<\/strong>
\nTobias Grosser, University of Cambridge, UK
\n<\/strong><\/p>\n

Abstract.<\/p>\n<\/td>\n<\/tr>\n

\n

Tools: Accelerator Code Generation<\/strong>
\nTobias Grosser, University of Cambridge, UK
\n<\/strong><\/p>\n

Abstract.<\/p>\n<\/td>\n<\/tr>\n

\n

Emerging ML Paradigms: Neuro-Inspired Computing<\/b>
\nJan Rabaey, UC Berkeley, USA<\/b><\/p>\n

Lessons from the brain and what it means for:
\n– ML hardware,
\n– Neuromorphic,
\n– Hyper-dimensional, etc.<\/p>\n<\/td>\n<\/tr>\n

\n

Emerging ML Paradigms: Towards Cognitive Systems<\/b>
\nJan Rabaey, UC Berkeley, USA<\/b><\/p>\n

– Autonomous sensor-control-actuation
\n– Model versus data driven
\n– Reinforcement learning
\n– Symbolic reasoning
\n– Probabilistic learning, graphs<\/p>\n<\/td>\n<\/tr>\n

\n

Efficient Execution of Approximated AI Algorithms on Heterogeneous Edge AI Systems <\/b>
\nDavid Atienza, EPFL, Switzerland<\/b><\/p>\n

i. Major challenges in designing energy-efficient edge AI architectures due to the complexity of AI\/CNN.
\nii. Design options to reduce complexity (pruning, quantization, etc.) and benefits of operating edge AI architectures at sub-nominal conditions.
\niii. New architectural design methodologies for edge AI systems, called Embedded Ensemble CNNs (E2CNNs) to conceive pruned CNNs and AI implementations with improved robustness against memory errors in pruned\/quantized single-instance ML\/CNNs.
\niv. Experimental evaluation of compression methods and design space exploration to produce an ensemble of CNNs for edge AI devices with the same memory requirements as the original architectures but improved error robustness (in different types of memories) for sub-threshold operation.<\/p>\n<\/td>\n<\/tr>\n

\n

Application-Driven System Design and Optimization flow of Edge AI Use Cases in Industrial and Medical Domains<\/b>
\nDavid Atienza, EPFL, Switzerland<\/b><\/p>\n

i. Overview of major key challenges in different industrial case studies for AI\/ML systems (computation vs communication and other trade-offs to consider particularly for medical applications in the context of Big Data healthcare).
\nii. Different design option for AI\/ML hardware systems using centralized vs. federated approaches on edge AI systems.
\niii. Mapping options for ULP multi-core embedded systems with neural network accelerators for energy-scalable software layers based on target applications.
\niv. Examples of next-generation of smart wearable devices in the healthcare context
\nv. Examples of industrial edge AI systems for home automation.<\/p>\n<\/td>\n<\/tr>\n

\n

Practical Case Studies: \u201cEnergy Efficient ML Applications for Metaverse\u201d<\/b>
\nHuichu Liu, Meta, USA<\/b><\/p>\n

– Overview of AR\/VR system features and energy constraints
\n– Breakdown different applications running on AR\/VR HW and its related ML algorithms
\n– HW techniques to enable energy efficient NN execution
\n– HW-SW techniques to enable efficient NN mapping
\n– Algorithm techniques for practical applications
\n– Future applications\/challenges\/research directions<\/p>\n<\/td>\n<\/tr>\n

\n

Cross-Layer Optimization<\/b>
\nMarian Verhelst, KU Leuven, Belgium<\/b><\/p>\n

– Need for optimization across the stack cross layer design space exploration
\n– Tools flows for cross layer optimization
\n– Final Q&A and adjourn<\/p>\n<\/td>\n<\/tr>\n

\"registration\"<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Scroll to Top<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

AbstractsPractical InformationCourse Material On-Line Class CET – Central European Time Zone Download One-Page Schedule Here Week 1: March 12-15, 2024 Week 2: March 18-22, 2024 Registration deadline: February 23, 2024 Payment deadline: March 1, 2024 TEACHING HOURS DAILY Central European Time CET Eastern Standard Time EST Pacific Standard Time PST India Standard Time IST Module<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[31],"tags":[],"class_list":["post-6874","post","type-post","status-publish","format-standard","hentry","category-on-line-class"],"yoast_head":"\nHardware-Efficient Edge AI - Mead Education<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Hardware-Efficient Edge AI - Mead Education\" \/>\n<meta property=\"og:description\" content=\"AbstractsPractical InformationCourse Material On-Line Class CET – Central European Time Zone Download One-Page Schedule Here Week 1: March 12-15, 2024 Week 2: March 18-22, 2024 Registration deadline: February 23, 2024 Payment deadline: March 1, 2024 TEACHING HOURS DAILY Central European Time CET Eastern Standard Time EST Pacific Standard Time PST India Standard Time IST Module\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/\" \/>\n<meta property=\"og:site_name\" content=\"Mead Education\" \/>\n<meta property=\"article:published_time\" content=\"2022-02-14T09:05:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-07T20:09:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png\" \/>\n<meta name=\"author\" content=\"Caroline\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Caroline\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/\"},\"author\":{\"name\":\"Caroline\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/#\\\/schema\\\/person\\\/68f80ae70ec539ddd927d312085b2f63\"},\"headline\":\"Hardware-Efficient Edge AI\",\"datePublished\":\"2022-02-14T09:05:54+00:00\",\"dateModified\":\"2024-03-07T20:09:45+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/\"},\"wordCount\":1369,\"image\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mead.ch\\\/mead\\\/wp-content\\\/uploads\\\/2013\\\/05\\\/registration.png\",\"articleSection\":[\"On-Line Class\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/\",\"url\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/\",\"name\":\"Hardware-Efficient Edge AI - Mead Education\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mead.ch\\\/mead\\\/wp-content\\\/uploads\\\/2013\\\/05\\\/registration.png\",\"datePublished\":\"2022-02-14T09:05:54+00:00\",\"dateModified\":\"2024-03-07T20:09:45+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/#\\\/schema\\\/person\\\/68f80ae70ec539ddd927d312085b2f63\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mead.ch\\\/mead\\\/wp-content\\\/uploads\\\/2013\\\/05\\\/registration.png\",\"contentUrl\":\"https:\\\/\\\/mead.ch\\\/mead\\\/wp-content\\\/uploads\\\/2013\\\/05\\\/registration.png\",\"width\":123,\"height\":40},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/hw-accelerated-machine-learning-at-the-edge\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mead.ch\\\/mead\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Hardware-Efficient Edge AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/#website\",\"url\":\"https:\\\/\\\/mead.ch\\\/mead\\\/\",\"name\":\"Mead Education\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mead.ch\\\/mead\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/mead.ch\\\/mead\\\/#\\\/schema\\\/person\\\/68f80ae70ec539ddd927d312085b2f63\",\"name\":\"Caroline\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g\",\"caption\":\"Caroline\"},\"url\":\"https:\\\/\\\/mead.ch\\\/mead\\\/author\\\/caroline\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Hardware-Efficient Edge AI - Mead Education","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/","og_locale":"en_US","og_type":"article","og_title":"Hardware-Efficient Edge AI - Mead Education","og_description":"AbstractsPractical InformationCourse Material On-Line Class CET – Central European Time Zone Download One-Page Schedule Here Week 1: March 12-15, 2024 Week 2: March 18-22, 2024 Registration deadline: February 23, 2024 Payment deadline: March 1, 2024 TEACHING HOURS DAILY Central European Time CET Eastern Standard Time EST Pacific Standard Time PST India Standard Time IST Module","og_url":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/","og_site_name":"Mead Education","article_published_time":"2022-02-14T09:05:54+00:00","article_modified_time":"2024-03-07T20:09:45+00:00","og_image":[{"url":"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png","type":"","width":"","height":""}],"author":"Caroline","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Caroline","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#article","isPartOf":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/"},"author":{"name":"Caroline","@id":"https:\/\/mead.ch\/mead\/#\/schema\/person\/68f80ae70ec539ddd927d312085b2f63"},"headline":"Hardware-Efficient Edge AI","datePublished":"2022-02-14T09:05:54+00:00","dateModified":"2024-03-07T20:09:45+00:00","mainEntityOfPage":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/"},"wordCount":1369,"image":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#primaryimage"},"thumbnailUrl":"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png","articleSection":["On-Line Class"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/","url":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/","name":"Hardware-Efficient Edge AI - Mead Education","isPartOf":{"@id":"https:\/\/mead.ch\/mead\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#primaryimage"},"image":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#primaryimage"},"thumbnailUrl":"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png","datePublished":"2022-02-14T09:05:54+00:00","dateModified":"2024-03-07T20:09:45+00:00","author":{"@id":"https:\/\/mead.ch\/mead\/#\/schema\/person\/68f80ae70ec539ddd927d312085b2f63"},"breadcrumb":{"@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#primaryimage","url":"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png","contentUrl":"https:\/\/mead.ch\/mead\/wp-content\/uploads\/2013\/05\/registration.png","width":123,"height":40},{"@type":"BreadcrumbList","@id":"https:\/\/mead.ch\/mead\/hw-accelerated-machine-learning-at-the-edge\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mead.ch\/mead\/"},{"@type":"ListItem","position":2,"name":"Hardware-Efficient Edge AI"}]},{"@type":"WebSite","@id":"https:\/\/mead.ch\/mead\/#website","url":"https:\/\/mead.ch\/mead\/","name":"Mead Education","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mead.ch\/mead\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/mead.ch\/mead\/#\/schema\/person\/68f80ae70ec539ddd927d312085b2f63","name":"Caroline","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/f522f149e06cb40cc9b2e4ff491495003929c3b56676afbdfd942e717747c828?s=96&d=blank&r=g","caption":"Caroline"},"url":"https:\/\/mead.ch\/mead\/author\/caroline\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p76pb6-1MS","_links":{"self":[{"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/posts\/6874","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/comments?post=6874"}],"version-history":[{"count":31,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/posts\/6874\/revisions"}],"predecessor-version":[{"id":9002,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/posts\/6874\/revisions\/9002"}],"wp:attachment":[{"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/media?parent=6874"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/categories?post=6874"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mead.ch\/mead\/wp-json\/wp\/v2\/tags?post=6874"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}