ML Conf EU 2020
as the organisers put it
ML conf EU is a place to learn all about the practical application of machine learning for engineers. On November 5-6, 2020 get a clearer idea of ML, and practice it for your own projects
| title | author | length |
|---|---|---|
| TensorFlow.js 101: ML in the Browser and Beyond | Jason Mayes | 41m |
TensorFlow.js runs full ML in-browser and on Node with concrete results: COCO‑SSD (90 classes) does real‑time webcam detection, FaceMesh is a 3 MB model with… | ||
| An Introduction to Transfer Learning in NLP and HuggingFace | Thomas Wolf | 32m |
Survey of how large pretrained transformer models (BERT/GPT/RoBERTa/T5 and distilled variants) use sequential transfer learning: large-scale self‑supervised… | ||
| Computer Vision Using OpenCV | Beril Sirmacek | |
Talk recording from ML conf. EU 2020
Website - https://mlconf.eu/
#Computer Vision Using OpenCV
As an AI scientist and a developer, Beril has been engaged… | ||
| How to Machine Learn-ify any Product | Shivani Poddar | 32m |
Replaces a ruley confirmation flow on Portal with a classifier that predicts which contact "John" means using organic confirmation labels from past prompts and… | ||
| The Evolution Revolution | Robert Plummer | 31m |
Argues that machine learning ops should implement once by writing core math in one language and transpiling to GPUs and runtimes, showing working JavaScript… | ||
| Teaching ML and AI to Coders | Laurence Moroney | 33m |
Explains a concrete program: a TensorFlow syllabus turned into three MOOCs (with deeplearning.ai), a YouTube channel, hands‑on codelabs, university… | ||
| Deep Transfer Learning for Computer Vision | Dipanjan Sarkar, Sachin Dangayach | 08m |
Nanoscale semiconductor defect pipelines combine fine-tuned ResNet50 deep features with traditional descriptors like Zernike moments and GLCM, fuse them into a… | ||
| Processing Robot Data at Scale with R and Kubernetes | Frans van Dunne | 08m |
R runs in Docker containers on Kubernetes to preprocess several hundred GB of compressed JSONL; Pachyderm pipelines version inputs and outputs so reruns… | ||
| Broadening AI Adoption with AutoML | Bernhard Suhm | 08m |
AutoML replaces repetitive pipeline steps with automated feature engineering, automated model selection and hyperparameter tuning, letting domain experts… | ||
| nothing matches | ||