It's well known that NNs are very vulnerable to adversarial interventions, e.g., indiscernible test-time attacks. But indiscriminate data poisoning, wherein the attacker modifies a small fraction of the training data to reduce the test accuracy, seems to be much harder! Why? 2/n
MACHINE LEARNING
-
Neural Networks Poisoning Attacks Research Paper Accepted
By
–
Paper accepted to @TmlrOrg
: "Indiscriminate Data Poisoning Attacks on Neural Networks," led by Yiwei Lu and co-advised with Yaoliang Yu. Neural networks are surprisingly hard to (indiscriminately) poison! We give better attacks. https://
openreview.net/forum?id=x4hmI
sWu7e
… 1/n -
AI Benefits Evolution: From Limited Use Cases to Practical Applications
By
–
I think that in the past the real benefits of AI were small or not present at all. E.g. you could train a RL agent but what it is for if it can’t be entertaining for player? Anyway, now things are changing.
-
LangChain Unstructured Integration for Data Cleaning
By
–
Before you can use LangChain with your data, you first need to clean it up. That's where an integration with @UnstructuredIO comes in Blog Post: https://
blog.langchain.dev/langchain-unst
ructured/
… We'll use Unstructured to power a lot of our document loaders: https://
langchain.readthedocs.io/en/latest/modu
les/document_loaders.html
… -
Groq Hiring Creative Problem Solvers for Machine Learning Systems
By
–
We're looking for creative problem solvers to help us build the next generation of #MachineLearning Systems! Apply here https://
groq.com/careers/?gh_ji
d=5090081003
… -
Critical Questions and Strategies for ML Dataset Lifecycle Management
By
–
The guide offers questions, suggestions, strategies, and resources while working with ML datasets at every phase of their lifecycle, and shows the benefits of working critically with them. It gives you the questions that we've found helpful in our work with large ML datasets.
-
Critical Field Guide for Working With Machine Learning Datasets Released
By
–
NEW: Today we release a 'Critical Field Guide for Working With Machine Learning Datasets' by @SarahCiston
. It's a practical guide to navigating datasets. If you're an engineer, designer, journalist artist, or a student who uses datasets, it's here for you. -
Polygon Annotation with CVAT: Quick 3-Minute Guide
By
–
🚀Polygon annotation using CVAT in 3 minutes!
— Satya Mallick (@LearnOpenCV) 6 février 2023
In this video, we export the dataset as segmentation mask images or in Cocoa Jason format.https://t.co/mYYWt65YhI #cvat #polygonannotation #annotation #dataset #cocoajasonformat #ai #computervision #deeplearning #machinelearning pic.twitter.com/usGeZFcpcTPolygon annotation using CVAT in 3 minutes!
In this video, we export the dataset as segmentation mask images or in Cocoa Jason format. https://
youtube.com/watch?v=YL0l2M
YUFC0
… #cvat #polygonannotation #annotation #dataset #cocoajasonformat #ai #computervision #deeplearning #machinelearning -
Visualizing Embeddings for Semantic Search Understanding
By
–
Step-3: Visualize the embeddings in the playground to understand how semantic search works. Semantically similar sentences would be dots closer to each other and vice-versa.
-
Semantic Search: Understanding Meaning Beyond Keywords
By
–
Semantic search is based on the idea of understanding the meaning and context of the words used in a query, rather than just matching the exact keywords to the documents. It focuses on finding relevant results that match the user's intention, rather than matching the keywords.