Our @FT weekend profile of Geoff Hinton, and why he’s speaking up, with
@RichardWaters
. Feat. long-time collaborators/peers Yoshua Bengio and Stuart Russell. https://
on.ft.com/3pbpVtR
MACHINE LEARNING
-
Geoff Hinton Speaks Out on AI Safety Concerns
By
–
-
Top Technical Talent in AI Industry Operating at Incredible Levels
By
–
heavily related: the level at which the top technical people in the world are operating is incredible to watch and makes me feel very fortunate to be in this industry!
-
Data Quality Emerges as Key Differentiator in AI Development
By
–
Hidden amongst the zingers in the leaked Google memo there's this: data quality is what is making the difference now. This is an important shift away from internet-scale garbage dump datasets that have been running the show for years.
-
Training an AI voice model to sing
By
–
Pour ceux qui croit qu’il suffit de cliquer sur un « bouton » pour avoir ce résultat allez voir la vidéo YouTube https://
youtu.be/ECIas_koYcI J’ai codé et testé des jours, en plus de dépenser des sous, pour entraîner un modèle de voix de Macron qui me permet de le faire chanter. -
Prompt engineering investigation: minimal sensitivity to formatting changes
By
–
We spent a lot of time investigating what others papers did (Chinchilla, GPT-3, PaLM) but very few of them actually provide any prompt so we just implemented what made sense to us. And we did not observe 20% differences by adding or removing a space in the prompt.
-
Formatting Alone Cannot Explain Performance Gap with LLaMA
By
–
I don't think that formatting alone can explain such a gap. You could maybe try to reproduce LLaMA numbers given the available model. It is likely that fixing these differences for LLaMA will also improve the numbers you report for your model.
-
LLaMA evaluation metrics concern and measurement discrepancies
By
–
It is true that accuracy on some metrics can be quite sensitive to the prompt, however this is not normal that all metrics reported for LLaMA here are systematically (and significantly) below what we measured. There may be an issue in how LLaMA was evaluated.
-
AI Data Pipeline: 5 Processing Steps and Storage Importance
By
–
What is an #AI Data Pipeline? Why does Storage Matter? https://
purefla.sh/3oUEnGm by @PureStorage This article addresses the 5 processing steps in the AI Data Pipeline Lifecycle:
1) Ingestion
2) Cleaning
3) Exploration
4) Training
5) Deployment
and
emphasizes The importance of the -
Storage Matters for AI and Machine Learning Beyond Buzzwords
By
–
See how Storage Matters to #AI and #MachineLearning in this @PureStorage webinar: "AI and ML — Beyond the Buzzwords into Reality with Pure1" at https://
purefla.sh/3nbDBo2 #PureStorage #BigData #Analytics #DataScience #StorageMatters ——
This webinar features:
◉ Stories with -
Cerebras Demonstrates Sparse Neural Network Hardware at ICLR2023
By
–
Cerebras sponsored the #ICLR2023 workshop on Sparsity in Neural Networks and presented "Sparse Pre-training and Dense Fine-tuning." Our hardware natively supports structured/dynamic sparsity, and we welcome collaboration on sparsity research!