A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations
暂无分享,去创建一个
[1] Jessica B. Hamrick,et al. Unifying Grokking and Double Descent , 2023, ArXiv.
[2] J. Steinhardt,et al. Progress measures for grokking via mechanistic interpretability , 2023, ICLR.
[3] Tom McGrath,et al. Tracr: Compiled Transformers as a Laboratory for Interpretability , 2023, ArXiv.
[4] J. Steinhardt,et al. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small , 2022, ArXiv.
[5] Tom B. Brown,et al. In-context Learning and Induction Heads , 2022, ArXiv.
[6] S. Kakade,et al. Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit , 2022, NeurIPS.
[7] J. Dean,et al. Emergent Abilities of Large Language Models , 2022, Trans. Mach. Learn. Res..
[8] Sébastien Bubeck,et al. Unveiling Transformers with LEGO: a synthetic reasoning task , 2022, ArXiv.
[9] Max Tegmark,et al. Towards Understanding Grokking: An Effective Theory of Representation Learning , 2022, NeurIPS.
[10] Tom B. Brown,et al. Predictability and Surprise in Large Generative Models , 2022, FAccT.
[11] D. Hassabis,et al. Acquisition of chess knowledge in AlphaZero , 2021, Proceedings of the National Academy of Sciences of the United States of America.
[12] Boaz Barak,et al. Revisiting Model Stitching to Compare Neural Representations , 2021, NeurIPS.
[13] Eran Yahav,et al. Thinking Like Transformers , 2021, ICML.
[14] Jaime Fern'andez del R'io,et al. Array programming with NumPy , 2020, Nature.
[15] Mark Chen,et al. Language Models are Few-Shot Learners , 2020, NeurIPS.
[16] Geoffrey E. Hinton,et al. Similarity of Neural Network Representations Revisited , 2019, ICML.
[17] Michael Carbin,et al. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.
[18] Jascha Sohl-Dickstein,et al. SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability , 2017, NIPS.
[19] Lukasz Kaiser,et al. Attention is All you Need , 2017, NIPS.
[20] Andy R. Terrel,et al. SymPy: Symbolic computing in Python , 2017, PeerJ Prepr..
[21] Hod Lipson,et al. Convergent Learning: Do different neural networks learn the same representations? , 2015, FE@NIPS.
[22] Wes McKinney,et al. Data Structures for Statistical Computing in Python , 2010, SciPy.
[23] Jonathan L. Alperin,et al. Groups and Representations , 1995 .