Princeton University

Meta Platforms, Inc.

Xiaoliang Dai

Niraj K Jha

Hongxu Yin

Peter Vajda

Peizhao Zhang

Yanghan Wang

Arsalan Mosenia

Prateek Mittal

Yuandong Tian

Bichen Wu

According to various embodiments, a method for generating a compact and accurate neural network for a dataset that has initial data and is updated with new data is disclosed. The method includes performing a first training on the initial neural network architecture to create a first trained neural network architecture. The method additionally includes performing a second training on the first trained neural network architecture when the dataset is updated with new data to create a second trained neural network architecture. The second training includes growing one or more connections for the new data based on a gradient of each connection, growing one or more connections for the new data and the initial data based on a gradient of each connection, and iteratively pruning one or more connections based on a magnitude of each connection until a desired neural network architecture is achieved.

System and method for incremental learning using a grow-and-prune paradigm with neural networks

Computer implemented systems are described that implement a differentiable neural architecture search (DNAS) engine executing on one or more processors. The DNAS engine is configured with a stochastic super net defining a layer-wise search space having a plurality of candidate layers, each of the candidate layers specifying one or more operators for a neural network architecture. Further, the DNAS engine is configured to process training data to train weights for the operators in the stochastic super net based on a loss function representing a latency of the respective operator on a target platform, and to select a set of candidate neural network architectures from the trained stochastic super net. The DNAS engine may, for example, be configured to train the stochastic super net by traversing the layer-wise search space using gradient-based optimization of network architecture distribution.

Hardware-aware efficient neural network design system having differentiable neural architecture search

According to various embodiments, a method for generating one or more optimal neural network architectures is disclosed. The method includes providing an initial seed neural network architecture and utilizing sequential phases to synthesize the neural network until a desired neural network architecture is reached. The phases include a gradient-based growth phase and a magnitude-based pruning phase.

Method and system for neural network synthesis

According to various embodiments, a method for locating the user of a mobile device without accessing global position system (GPS) data is disclosed. The method includes determining the last location that the user was connected to a wireless network. The method further includes compiling publicly-available auxiliary information related to the last location. The method additionally includes classifying an activity of the user to driving, traveling on a plane, traveling on a train, or walking. The method also includes estimating the location of the user based on sensory and non-sensory data of the mobile device particular to the activity classification of the user.

System and method for tracking a mobile device user

Growing community of inventors

Princeton, NJ, United States of America

Xiaoliang Dai