In Advances in Neural Information Processing Systems

By Christopher K. I. Williams, David S. Touretzky, M. Mozer, Carl E. Rasmussen, Michael E. Hasselmo, RegressionChristopher, I. K, WilliamsNeural, GroupAston, UniversityBirmingham. 1996

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Llama 2: Open Foundation and Fine-Tuned Chat Models (2023, methodology): “We observe that only HellaSwag and MMLU-Humanities appear to have been boosted due to contamination in the training data, with the 70B model appearing to have gained a greater benefit than the 7B model, as one might expect.”
Persistent Anti-Muslim Bias in Large Language Models (2021, background): “These language models have evolved, from learning individual word vectors with single-layer models (1), to more complex language generation architectures such as recurrent neural networks (2) and most recently transformers (3–5).”
Density estimation using Real NVP (2016, background): “As the existence proof of nonlinear ICA solutions [24] suggests, auto-regressive models can be seen as tractable instance of maximum likelihood nonlinear ICA, where the residual corresponds to the independent components.”
Artificial Intelligence, Values, and Alignment (2020, background): “In fact, ordinary moral disagreement between groups has been a persistent source of conﬂict in human life (Haidt, 2012).”
Self-critiquing models for assisting human evaluators (2022, background): “Feedback in preference learning [CLB17] is very information-sparse, and humans typically spend several minutes on a comparison yielding a single bit of information.”
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth (2021, background): “[DKB20] studied rank collapse in randomly initialized linear and ReLU networks and showed that batch normalization is an effective mitigation strategy.”
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning (2020, neutral): “The ﬁlter value is set to zero for all instances that do not have the same type of a given question [Liu et al. , 2019].”
Time-series forecasting with deep learning: a survey (2020, background): “In addition, Gaussian processes [21] have been extensively used for time-series prediction—with recent extensions including deep Gaussian processes [22], and parallels in deep learning via neural processes [23].”
Data Poisoning against Differentially-Private Learners: Attacks and Defenses (2019, background): “In data poisoning attacks [Biggio et al., 2012; Koh et al., 2018; Mei and Zhu, 2015; Alfeld et al., 2016; Li et al., 2016; Xiao et al., 2015; Muñoz-González et al., 2017; Jun et al., 2018; Zhao et al., 2017; Zhang and Zhu, 2019], the adversary corrupts examples at training time to manipulate the lea”
On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimization (2017, methodology): “Similar averaging approaches have been proposed in the literature, see [Hazan and Kale, 2014; Johnson and Zhang, 2013; Smith et al., 2016; Zhang et al., 2016; Loshchilov and Hutter, 2016; Chen et al., 2016; Wang et al., 2017].”