• Publications
  • Influence
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
TLDR
We reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al. (2017) as a method for probabilistic inference in a hierarchical Bayesian model. Expand
  • 213
  • 22
  • PDF
A new glucagon and GLP-1 co-agonist eliminates obesity in rodents.
We report the efficacy of a new peptide with agonism at the glucagon and GLP-1 receptors that has potent, sustained satiation-inducing and lipolytic effects. Selective chemical modification toExpand
  • 389
  • 15
  • PDF
Adipocyte LDL receptor-related protein-1 expression modulates postprandial lipid transport and glucose homeostasis in mice.
Diet-induced obesity and its serious consequences such as diabetes, cardiovascular disease, and cancer are rapidly becoming a major global health threat. Therefore, understanding the cellular andExpand
  • 136
  • 7
  • PDF
Melanocortin signaling in the CNS directly regulates circulating cholesterol
Cholesterol circulates in the blood in association with triglycerides and other lipids, and elevated blood low-density lipoprotein cholesterol carries a risk for metabolic and cardiovascularExpand
  • 86
  • 6
Restoration of leptin responsiveness in diet‐induced obese mice using an optimized leptin analog in combination with exendin‐4 or FGF21
The identification of leptin as a mediator of body weight regulation provided much initial excitement for the treatment of obesity. Unfortunately, leptin monotherapy is insufficient in reversingExpand
  • 115
  • 4
Defective Lipid Delivery Modulates Glucose Tolerance and Metabolic Response to Diet in Apolipoprotein E–Deficient Mice
OBJECTIVE—Apolipoprotein E (ApoE) regulates plasma lipid levels via modulation of lipolysis and serving as ligand for receptor-mediated clearance of triglyceride (TG)-rich lipoproteins. This studyExpand
  • 82
  • 3
  • PDF
Reconciling meta-learning and continual learning with online mixtures of tasks
TLDR
We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. Expand
  • 26
  • 2
  • PDF
Engaging with communities to foster health: the experience of inner-city children and families with learning circles.
The authors briefly introduce a clinical outreach initiative that is innovative because of the types of partnerships that have been formed within an inner-city community context. The initiative wasExpand
  • 7
  • 1
The Cognitive Symmetry Engine : An Active Approach to Knowledge
Knowledge acquisition and representation is an integral part of an active cognitive system, and such systems are continuously updating their knowledge of their own embodiment, the external world andExpand
  • 2
  • 1
  • PDF
Form seeking function: An exploratory content analysis evaluation of the imagery contained in law enforcement agency police officer recruitment brochures
The current exploratory study incorporates conceptual content analysis as a means of examining the imagery contained within a selected sample of police department recruitment brochures. The studyExpand
  • 3
  • 1