#ai
Allen AI's new model based on its high quality text including academic publication corpus.
OLMo Suite - a allenai Collection
https://huggingface.co/collections/allenai/olmo-suite-65aeaae8fe5b6b2122b46778
Allen AI's new model based on its high quality text including academic publication corpus.
OLMo Suite - a allenai Collection
https://huggingface.co/collections/allenai/olmo-suite-65aeaae8fe5b6b2122b46778
huggingface.co
OLMo Suite - a allenai Collection
Artifacts for the first set of OLMo models.
🔥1
#ml
Jelassi S, Brandfonbrener D, Kakade SM, Malach E. Repeat after me: Transformers are better than state space models at copying. arXiv [cs.LG]. 2024. Available: http://arxiv.org/abs/2402.01032
Not surprising at all when you have direct access to a long context. But hey, look at this title.
Jelassi S, Brandfonbrener D, Kakade SM, Malach E. Repeat after me: Transformers are better than state space models at copying. arXiv [cs.LG]. 2024. Available: http://arxiv.org/abs/2402.01032
Not surprising at all when you have direct access to a long context. But hey, look at this title.
arXiv.org
Repeat After Me: Transformers are Better than State Space Models at Copying
Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on the sequence length, which we...
👍1
#ml
I got interested in satellite data last year and played with it a bit. It's fantastic. The spatiotemporal nature of it brings up a lot of interesting questions.
Then I saw this paper today:
Rolf, Esther, Konstantin Klemmer, Caleb Robinson, and Hannah Kerner. 2024. “Mission Critical -- Satellite Data Is a Distinct Modality in Machine Learning.” arXiv [Cs.LG], February. http://arxiv.org/abs/2402.01444.
I got interested in satellite data last year and played with it a bit. It's fantastic. The spatiotemporal nature of it brings up a lot of interesting questions.
Then I saw this paper today:
Rolf, Esther, Konstantin Klemmer, Caleb Robinson, and Hannah Kerner. 2024. “Mission Critical -- Satellite Data Is a Distinct Modality in Machine Learning.” arXiv [Cs.LG], February. http://arxiv.org/abs/2402.01444.
arXiv.org
Mission Critical -- Satellite Data is a Distinct Modality in...
Satellite data has the potential to inspire a seismic shift for machine learning -- one in which we rethink existing practices designed for traditional data modalities. As machine learning for...
❤3
👍1
#ai
Gemini Ultra vs GPT-4: Google Still Lacks the Secret Sauce | Beebom
https://beebom.com/gemini-ultra-vs-gpt-4/
Gemini Ultra vs GPT-4: Google Still Lacks the Secret Sauce | Beebom
https://beebom.com/gemini-ultra-vs-gpt-4/
Beebom
Gemini Ultra vs GPT-4: Google Still Lacks the Secret Sauce
We have done a thorough comparison between Gemini vs GPT-4 to evaluate their commonsense reasoning, coding performance, and more.
👍1
#misc
Walking in the dark is different for women and men.
Chaney, Robert A., Alyssa Baer, and L. Ida Tovar. 2023. “Gender-Based Heat Map Images of Campus Walking Settings: A Reflection of Lived Experience.” Violence and Gender, December. https://doi.org/10.1089/vio.2023.0027.
Walking in the dark is different for women and men.
Chaney, Robert A., Alyssa Baer, and L. Ida Tovar. 2023. “Gender-Based Heat Map Images of Campus Walking Settings: A Reflection of Lived Experience.” Violence and Gender, December. https://doi.org/10.1089/vio.2023.0027.
🤔1
#ml
Like a dictionary
Kunc, Vladim’ir, and Jivr’i Kl’ema. 2024. “Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks.” arXiv [Cs.LG], February. http://arxiv.org/abs/2402.09092.
Like a dictionary
Kunc, Vladim’ir, and Jivr’i Kl’ema. 2024. “Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks.” arXiv [Cs.LG], February. http://arxiv.org/abs/2402.09092.
arXiv.org
Three Decades of Activations: A Comprehensive Survey of 400...
Neural networks have proven to be a highly effective tool for solving complex problems in many areas of life. Recently, their importance and practical usability have further been reinforced with...
🔥1
#ai
Google released new models. Those models are easier to use than llama 2.
https://www.kaggle.com/models/google/gemma
https://blog.google/technology/developers/gemma-open-models/
Google released new models. Those models are easier to use than llama 2.
https://www.kaggle.com/models/google/gemma
https://blog.google/technology/developers/gemma-open-models/
Kaggle
Google | Gemma | Kaggle
Gemma is a family of lightweight, open models built from the research and technology that Google used to create the Gemini models.
🔥1
5_4_800_36_downscaled.gif
54.4 MB
#misc
Animation of some periodic 3-body problems. How pretty.
https://en.wikipedia.org/wiki/Three-body_problem#/media/File:5_4_800_36_downscaled.gif
Animation of some periodic 3-body problems. How pretty.
https://en.wikipedia.org/wiki/Three-body_problem#/media/File:5_4_800_36_downscaled.gif
❤1👍1
#dev
https://substack.com/redirect/4af1baf3-a4d7-48d1-9592-5ea0971a056a?j=eyJ1IjoiNHowa3gifQ.QnwKDJ1CRSD1ToSPhPzIWMi45g-Rid7OgDj8cqSear0
Sounds good but please DO NOT USE upper cases. It is not only about PEP8 but more about consistency and cognitive load.
We solve this problem by writing down the dimensions in the docstrings and also include the math expressions there. But it is already obvious that writing down the dimensions in the var names makes things much easier.
https://substack.com/redirect/4af1baf3-a4d7-48d1-9592-5ea0971a056a?j=eyJ1IjoiNHowa3gifQ.QnwKDJ1CRSD1ToSPhPzIWMi45g-Rid7OgDj8cqSear0
Sounds good but please DO NOT USE upper cases. It is not only about PEP8 but more about consistency and cognitive load.
We solve this problem by writing down the dimensions in the docstrings and also include the math expressions there. But it is already obvious that writing down the dimensions in the var names makes things much easier.
Medium
Shape Suffixes — Good Coding Style
If you code neural networks, I believe that this convention can make your life more pleasant. We keep this pretty religiously at…
👍2
#fun
This is so cool. Would love to see some results for choice overload in foraging.
https://podcasts.google.com/feed/aHR0cHM6Ly9kYXRhc2tlcHRpYy5saWJzeW4uY29tL3Jzcw/episode/OTViNjcxYWUtMWI4Ny00NDVjLWJmNGEtN2FiODkyNzQ0ZjQ2?ep=14
This is so cool. Would love to see some results for choice overload in foraging.
https://podcasts.google.com/feed/aHR0cHM6Ly9kYXRhc2tlcHRpYy5saWJzeW4uY29tL3Jzcw/episode/OTViNjcxYWUtMWI4Ny00NDVjLWJmNGEtN2FiODkyNzQ0ZjQ2?ep=14
Google Podcasts
Data Skeptic - Optimal Foraging
Claire Hemmingway, an assistant professor in the Department of Psychology and Ecology and Evolutionary Biology at the University of Tennessee in Knoxville, is our guest today. Her research is on decision-making in animal cognition, focusing on neotropical…
👍1