Piero Molino

Piero Molino
3 POSTS 0 COMMENTS
Piero Molino is a Senior Research Scientist at Uber AI. He works on natural language understanding and conversational AI. He is a co-founder of Uber AI.

Engineering Blog Articles

Introducing Ludwig, a Code-Free Deep Learning Toolbox

Uber AI developed Ludwig, a code-free deep learning toolbox, to make deep learning more accessible to non-experts and enable faster model iteration cycles.

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

As powerful and widespread as convolutional neural networks are in deep learning, AI Labs’ latest research reveals both an underappreciated failing and a simple fix.

COTA: Improving Uber Customer Care with NLP & Machine Learning

In this article, Uber Engineering introduces our Customer Obsession Ticket Assistant (COTA), a new tool that puts machine learning and natural language processing models in the service of customer care to help agents deliver improved support experiences.

Research Papers

Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models

J. Zhang, Y. Wang, P. Molino, L. Li, D. Ebert
Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation, debugging, and comparison of machine learning models in a more transparent and interactive manner. [...] [PDF]
IEEE Visualization (IEEE VIS), 2018

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

R. Liu, J. Lehman, P. Molino, F.i Such, E. Frank, A. Sergeev, J. Yosinski
Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional neural networks may be appropriate. In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x,y) Cartesian space and one-hot pixel space. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2018

Characterizing how Visual Question Answering models scale with the world

E. Bingham, P. Molino, P. Szerlip, F. Obermeyer, N. Goodman
Detecting differences in generalization ability between models for visual question answering tasks has proven to be surprisingly difficult. We propose a new statistic, asymptotic sample complexity, for model comparison, and construct a synthetic data distribution to compare a strong baseline CNN-LSTM model to a structured neural network with powerful inductive biases. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2017

Characterizing how Visual Question Answering models scales with world

E. Bingham, P. Molino, P. Szerlip, F. Obermeyer, N. Goodman
Detecting differences in generalization ability between models for visual question answering tasks has proven to be surprisingly difficult. We propose a new statistic, asymptotic sample complexity, for model comparison, and construct a synthetic data distribution to compare a strong baseline CNN-LSTM model to a structured neural network with powerful inductive biases. [...] [PDF]
Advances in Neural Information Processing Systems (NIPS), 2017

Popular Articles