
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
While designing inductive bias in neural architectures has been widely s...
read it

Mathematical Reasoning via Selfsupervised Skiptree Training
We examine whether selfsupervised language modeling applied to mathemat...
read it

Mathematical Reasoning in Latent Space
We design and conduct a simple experiment to study whether neural networ...
read it

Learning to Reason in Large Theories without Imitation
Automated theorem proving in large theories can be learned via reinforce...
read it

Graph Representations for HigherOrder Logic and Theorem Proving
This paper presents the first use of graph neural networks (GNNs) for hi...
read it

HOList: An Environment for Machine Learning of HigherOrder Theorem Proving (extended version)
We present an environment, benchmark, and deep learning driven automated...
read it

HOList: An Environment for Machine Learning of HigherOrder Theorem Proving
We present an environment, benchmark, and deep learning driven automated...
read it

Text Embeddings for Retrieval From a Large Knowledge Base
Text embedding representing natural language documents in a semantic vec...
read it

HolStep: A Machine Learning Dataset for Higherorder Logic Theorem Proving
Large computerunderstandable proofs consist of millions of intermediate...
read it

Deep Network Guided Proof Search
Deep learning techniques lie at the heart of several significant AI adva...
read it

DeepMath  Deep Sequence Models for Premise Selection
We study the effectiveness of neural sequence models for premise selecti...
read it

Inceptionv4, InceptionResNet and the Impact of Residual Connections on Learning
Very deep convolutional networks have been central to the largest advanc...
read it

Large Scale Business Discovery from Street Level Imagery
Search with local intent is becoming increasingly useful due to the popu...
read it

SSD: Single Shot MultiBox Detector
We present a method for detecting objects in images using a single deep ...
read it

Rethinking the Inception Architecture for Computer Vision
Convolutional networks are at the core of most stateoftheart computer...
read it

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Training Deep Neural Networks is complicated by the fact that the distri...
read it

Training Deep Neural Networks on Noisy Labels with Bootstrapping
Current stateoftheart deep learning systems for visual object recogni...
read it

Explaining and Harnessing Adversarial Examples
Several machine learning models, including neural networks, consistently...
read it

Scalable, HighQuality Object Detection
Current highquality object detection approaches use the scheme of salie...
read it

Going Deeper with Convolutions
We propose a deep convolutional neural network architecture codenamed "I...
read it

Intriguing properties of neural networks
Deep neural networks are highly expressive models that have recently ach...
read it

DeepPose: Human Pose Estimation via Deep Neural Networks
We propose a method for human pose estimation based on Deep Neural Netwo...
read it

Scalable Object Detection using Deep Neural Networks
Deep convolutional neural networks have recently achieved stateofthea...
read it
Christian Szegedy
is this you? claim profile
Staff Research Scientist at Google since 2015, Senior Research Scientist at Google 2015, Software engineer at Google from 20102015, Research Scientist at Cadence Design Systems from 20052010, Research Assistant at University of Bonn from 19982005.