Most Popular Books by Mike Wu

"A panda has joined the animals, and she''s a painter like Ellie! Is there room for two artists at the zoo?"--Page 2 of cover

On the train ride to visit his grandpa, or Papa, Henri is only interested in his game. But then George the dog steals Henri''s hat upon arrival, so Henri makes chase and finds himself in front of a trunk full of hats. Henri tries on each hat . . . and imagines himself a race car driver, a sea captain, a flying ace, and more! Papa finally catches up to Henri and George, and that''s when Henri hears Papa''s stories, real stories, about racing, sailing, flying, and more! As Henri heads home, he looks up at the stars and begins to dream . . . of being just like Papa.

Since Ellie saved her home with her wonderful paintings, the zoo is back in business and the animals are more energetic than ever. All except for Lucy the giraffe, who hasn''t been able to sleep with all the noise. Determined to help her friend, Ellie tries to tone down the ruckus and organizes the animals into an orchestra. But is it possible to conduct the cacophony of the zoo into beautiful music? Praise for Ellie "[Wu''s] visual storytelling, rendered in sweet, throwback-style watercolors, shows creativity and poise. . . .

Ellie and her signature paintbrush guide the littlest readers through vibrant colors in this adorable board book by author-illustrator Mike Wu, illustrating how colors come together to create a beautiful picture.

Ellie. La elefantita creativa es una entrañable historia que celebra la creatividad y el uso de la imaginación, hasta tal punto que convierte estos valores en la solución al problema que se plantea en el libro. Los niños y niñas se sentirán inspirados a crear como Ellie. ¡El zoo cierra sus puertas! Para Ellie y sus amigos el zoo es su hogar y harán todo lo posible por salvarlo. Pero Ellie es solo un elefante bebé, y ella no sabe qué puede hacer para ayudar. Mientras los otros animales han encontrado una tarea que llevar a cabo y ya están manos a la obra, Ellie está triste porque no se le ocurre nada que ella sepa hacer muy bien para colaborar... Hasta que encuentra un pincel y algunas pinturas, y deja volar su imaginación, de manera que le da al zoo un gran chapoteo de color. ¿Será suficiente el brillante talento de Ellie para mantener abiertas las puertas del zoológico para siempre? A veces tendemos a compararnos con los demás y a pensar que no somos tan válidos como ellos. Pero si nos damos una oportunidad y confiamos en nosotros mismos, descubriremos cualidades que ni siquiera sabíamos que teníamos. ENGLISH DESCRIPTION The zoo is closing! Ellie and her friends want to save their home, but Ellie''s just a baby elephant, and she doesn''t know what she can do to help. While the other animals are busy working, Ellie finds a brush and some paints, and gives the zoo a big splash of color! Will her bright new talent be enough to keep the zoo''s gates open for good?"

Despite the growth of data size, many applications for which we would like to apply learning algorithms to are limited by data quantity and quality. Generative models propose a framework to naturally combine prior beliefs with real world data. Core to the generative approach is the challenge of probabilistic inference, or estimating latent variables given observations. This challenge has led to a rich field of research spanning many statistical techniques. More recently, deep learning methods have been used to solve inference queries, aptly named deep inference. In my dissertation I will explore extensions to deep inference in response to real world challenges of sparsity and efficiency. I will present case studies of practical applications where deep inference achieves considerable improvements upon prior work. This dissertation is centered around three parts. We present the background for generative models and deep inference with an emphasis on modern variational methods. The first part will present new algorithms for generalizing inference to be robust to different notions of sparsity, such as multimodal data, missing data, or computational constraints. Second, we study meta-amortized inference, or "inferring how to infer". A doubly-amortized inference algorithm would be cheaply able to solve inference queries for a novel generative model. We will show a new algorithm to re-purpose masked language modeling to do just this. Third, we present two real-world applications of deep inference in education: (a) estimating student abilities under item response theory and related psychometric models, and (b) inferring educational feedback for students learning to solve programming questions. Together, these contributions showcase the richness and utility of deep inference in education, and more broadly in real world contexts.