Yes! The trade-off gets better if you have more moments for the underlying distribution (versus just a variance). We have the theorem in the paper.
MACHINE LEARNING
-
Nominate Ethical Machine Learning Projects for Recognition
By
–
We're on the lookout for machine learning projects that showcase a commitment to ethics! Visit the link in this tweet to nominate Spaces that you think should be featured
-
AI Integration Across Business Drives Competitive Advantage and Growth
By
–
Integrating AI solutions into all aspects of the business is crucial for boosting competitive advantage and driving growth. Via @ingliguori #AI #DataScience #DigitalStrategy #DigitalTwins #Metaverse #digitaltransformation #MachineLearning #Healthtech #fintech #medtech #edutech
-
Adding ‘Exclude special tokens’ changes AI classifier output
By
–
Found that adding "Exclude the use of special tokens" at the end of each ChatGPT prompt has consistently changed the AI Text Classifier output from "likely AI generated" to "possibly AI generated" Either a coincidence, or special tokens are watermarking ChatGPT outputs.
-
Top 20 Canada Tech Provider Accelerates AI Inference
By
–
Honored to be chosen as one of @evbizmag
's "Top 20 Canada Technology Solution Providers 2022"! We're committed to making a difference in #tech by accelerating #AI #inference for diverse #neuralnetworks using our #energycentric computing architecture. https://
bit.ly/3wIBmtx -
Flan-T5 Outperforms T5 in Finetuning Efficiency
By
–
Key takeaway: finetuning Flan-T5 is better and more compute-efficient than finetuning T5. In other words, Flan-T5 > T5 for every real scenario I can think of. Don't use the pre-trained checkpoint—always finetune!
-
Fiverr adds AI Services to attract AI-savvy freelancers
By
–
Fiverr looking to attract AI-savvy freelancers as it adds "AI Services" to platform: https://
fiverr.com/cp/ai-services -
Google releases instruction tuning collection for improved language model reasoning
By
–
Today we’re releasing a new collection of tasks, templates and methods for instruction tuning of #ML models. Training on this collection can enable language models to reason more competently over arbitrary, unseen tasks. Learn all about it at: https://
goo.gle/3XWlqjc -
Transformer Variations: Major Refactoring Update Three Years Later
By
–
Cannot believe it is almost 3 years since my 2020 post on variations of Transformer. I spent some time and did a big refactoring of that old post with new section structure and new papers. Still missing a few items tho, will add them in slowly:
-
Blind AI Agents Learn Navigation Through Emergent Neural Representations
By
–
We train blind AI agents to navigate — i.e. no sensory input other than ego-motion and found the emergence of wall-following, collision-detection neurons, and map-like representations in their memories. This provides new insights into the success of 'map-free' navigation agents.