Search Results for author: Christian Szegedy

Found 28 papers, 16 papers with code

Autoformalization with Large Language Models

no code implementations25 May 2022 Yuhuai Wu, Albert Q. Jiang, Wenda Li, Markus N. Rabe, Charles Staats, Mateja Jamnik, Christian Szegedy

Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs.

 Ranked #1 on Automated Theorem Proving on miniF2F-test (using extra training data)

Automated Theorem Proving Program Synthesis

Memorizing Transformers

2 code implementations ICLR 2022 Yuhuai Wu, Markus N. Rabe, DeLesley Hutchins, Christian Szegedy

Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights.

Language Modelling Math

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

1 code implementation15 Jan 2021 Yuhuai Wu, Markus Rabe, Wenda Li, Jimmy Ba, Roger Grosse, Christian Szegedy

While designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks.

Inductive Bias Mathematical Reasoning

Mathematical Reasoning in Latent Space

no code implementations ICLR 2020 Dennis Lee, Christian Szegedy, Markus N. Rabe, Sarah M. Loos, Kshitij Bansal

We design and conduct a simple experiment to study whether neural networks can perform several steps of approximate reasoning in a fixed dimensional latent space.

Mathematical Reasoning

Learning to Reason in Large Theories without Imitation

no code implementations25 May 2019 Kshitij Bansal, Christian Szegedy, Markus N. Rabe, Sarah M. Loos, Viktor Toman

Our experiments show that the theorem prover trained with this exploration mechanism outperforms provers that are trained only on human proofs.

Automated Theorem Proving Imitation Learning +2

Graph Representations for Higher-Order Logic and Theorem Proving

no code implementations24 May 2019 Aditya Paliwal, Sarah Loos, Markus Rabe, Kshitij Bansal, Christian Szegedy

This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain.

Automated Theorem Proving

Text Embeddings for Retrieval From a Large Knowledge Base

no code implementations ICLR 2019 Tolgahan Cakaloglu, Christian Szegedy, Xiaowei Xu

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup.

Open-Domain Question Answering Retrieval

Deep Network Guided Proof Search

no code implementations24 Jan 2017 Sarah Loos, Geoffrey Irving, Christian Szegedy, Cezary Kaliszyk

Here we suggest deep learning based guidance in the proof search of the theorem prover E. We train and compare several deep neural network models on the traces of existing ATP proofs of Mizar statements and use them to select processed clauses during proof search.

Game of Go Image Captioning +5

DeepMath - Deep Sequence Models for Premise Selection

2 code implementations NeurIPS 2016 Alex A. Alemi, Francois Chollet, Niklas Een, Geoffrey Irving, Christian Szegedy, Josef Urban

We study the effectiveness of neural sequence models for premise selection in automated theorem proving, one of the main bottlenecks in the formalization of mathematics.

Automated Theorem Proving

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

79 code implementations23 Feb 2016 Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi

Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network.

Classification General Classification +2

Large Scale Business Discovery from Street Level Imagery

no code implementations17 Dec 2015 Qian Yu, Christian Szegedy, Martin C. Stumpe, Liron Yatziv, Vinay Shet, Julian Ibarz, Sacha Arnoud

Precise business store front detection enables accurate geo-location of businesses, and further provides input for business categorization, listing generation, etc.

SSD: Single Shot MultiBox Detector

221 code implementations8 Dec 2015 Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg

Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.

LIDAR Semantic Segmentation Node Property Prediction +2

Batch Normalization: Accelerating Deep Network Training byReducing Internal Covariate Shift

no code implementations ICML 2015 2015 Sergey Ioffe, Christian Szegedy

Training Deep Neural Networks is complicated by the factthat the distribution of each layer’s inputs changes duringtraining, as the parameters of the previous layers change. This slows down the training by requiring lower learningrates and careful parameter initialization, and makes it no-toriously hard to train models with saturating nonlineari-ties.

General Classification Image Classification +1

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

73 code implementations11 Feb 2015 Sergey Ioffe, Christian Szegedy

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.

Ranked #461 on Image Classification on ImageNet (Number of params metric, using extra training data)

General Classification Image Classification +1

Explaining and Harnessing Adversarial Examples

58 code implementations20 Dec 2014 Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence.

Image Classification Test

Scalable, High-Quality Object Detection

no code implementations3 Dec 2014 Christian Szegedy, Scott Reed, Dumitru Erhan, Dragomir Anguelov, Sergey Ioffe

Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with $0. 5$ mAP for a single model and $0. 52$ mAP for an ensemble of two models.

object-detection Object Detection +1

Going Deeper with Convolutions

80 code implementations CVPR 2015 Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).

General Classification Image Classification +2

Intriguing properties of neural networks

11 code implementations21 Dec 2013 Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks.

Scalable Object Detection using Deep Neural Networks

6 code implementations CVPR 2014 Dumitru Erhan, Christian Szegedy, Alexander Toshev, Dragomir Anguelov

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012).

object-detection Object Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.