W := (M₃ × T² × H_{P₅} × S¹) / ~_{BII} (@Obius_Maximus)

Claude의 출력과 오토인코더를 결합해 새로운 모델을 훈련했다는 주장에 대해, 이는 신뢰할 수 없는 마커에 기반한 확률적 설명일 뿐이라는 반박이 제기됐다. 모델 해석과 학습 신호의 신뢰성에 대한 기술적 논쟁으로, AI 연구자들에게 의미 있는 내용이다.

https://x.com/Obius_Maximus/status/2052904599213019200

#claude #autoencoders #modeltraining #llm #airesearch

Dan McAteer (@daniel_mac8)

Anthropic의 Natural Language Autoencoders가 LLM 메커니즘 해석 가능성 연구에서 매우 인상적인 성과로 언급됐다. 모델의 activation을 언어로 설명하게 하는 접근이 핵심이다.

https://x.com/daniel_mac8/status/2052812665613939066

#anthropic #llm #interpretability #research #autoencoders

Natural Language Autoencoders: Turning Claude's Thoughts into Text

https://www.anthropic.com/research/natural-language-autoencoders

#HackerNews #NaturalLanguageProcessing #Autoencoders #Claude #AIResearch #TextGeneration

When Dimensionality Hurts: The Role of #LLM Embedding Compression for Noisy Regression Tasks https://d.repec.org/n?u=RePEc:arx:papers:2502.02199&r=&r=cmp
"… suggest that the optimal dimensionality is dependent on the signal-to-noise ratio, exposing the necessity of feature compression in high noise environments. The implication of the result is that researchers should consider the #noise of a task when making decisions about the dimensionality of text.

… findings indicate that sentiment and emotion-based representations do not provide inherent advantages over learned latent features, implying that their previous success in similar tasks may be attributed to #regularisation effects rather than intrinsic informativeness."
#ML #autoencoders #Overfitting

'Manifold Learning by Mixture Models of VAEs for Inverse Problems', by Giovanni S. Alberti, Johannes Hertrich, Matteo Santacesaria, Silvia Sciutto.

http://jmlr.org/papers/v25/23-0396.html

#autoencoders #manifold #manifolds

'The Power of Contrast for Feature Learning: A Theoretical Analysis', by Wenlong Ji, Zhun Deng, Ryumei Nakada, James Zou, Linjun Zhang.

http://jmlr.org/papers/v24/21-1501.html

#autoencoders #supervised #generative

'Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders', by Lisa Bonheme, Marek Grzes.

http://jmlr.org/papers/v24/21-1145.html

#autoencoders #disentangled #representations

New preprint from our group ! 🧠 💻

*Whole-brain modelling of low-dimensional manifold modes reveals organising principle of brain dynamics*
https://www.biorxiv.org/content/10.1101/2023.11.20.567824v1

#brain #modeling #autoEncoders #variationalAutoEncoder #restingStateNetworks #manifold

real-time #anomaly detection
#python #algorithm
#autoencoders #machinelarning TensorFlow User Group (TFUG) Keras scikit-learn #neuralnetwork
#NAB #dataset ambient #temperature from a system that experienced a failure.
#risk #monitoring #maintenance

http://newdigitals.org/2023/10/23/real-time-anomaly-detection-of-nab-ambient-temperature-readings-using-the-tensorflow-keras-autoencoder/