Search Results for author:
Found 30 papers, 17 papers with code
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts.
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems.
Magnushammer: A Transformer-Based Approach to Premise Selection
By combining \method with a language-model-based automated theorem prover, we further improve the state-of-the-art proof success rate from $57. 0\%$ to $71. 0\%$ on the PISA benchmark using $4$x fewer parameters.
Autoformalization with Large Language Models
Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs.
Memorizing Transformers
Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights.
Hierarchical Transformers Are More Efficient Language Models
Transformer models yield impressive results on many NLP and sequence modeling tasks.
Ranked #8 on
Image Generation
on ImageNet 32x32
(bpd metric)
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
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.
Mathematical Reasoning via Self-supervised Skip-tree Training
We examine whether self-supervised language modeling applied to mathematical formulas enables logical reasoning.
Mathematical Reasoning in Latent Space
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.
Learning to Reason in Large Theories without Imitation
Our experiments show that the theorem prover trained with this exploration mechanism outperforms provers that are trained only on human proofs.
Ranked #3 on
Automated Theorem Proving
on HOList benchmark
Graph Representations for Higher-Order Logic and Theorem Proving
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.
Ranked #1 on
Automated Theorem Proving
on HOList benchmark
HOList: An Environment for Machine Learning of Higher-Order Theorem Proving
We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic.
Ranked #2 on
Automated Theorem Proving
on HOList benchmark
Text Embeddings for Retrieval From a Large Knowledge Base
Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup.
HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving
We propose various machine learning tasks that can be performed on this dataset, and discuss their significance for theorem proving.
Ranked #3 on
Automated Theorem Proving
on HolStep (Unconditional)
Deep Network Guided Proof Search
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.
DeepMath - Deep Sequence Models for Premise Selection
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.
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
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.
Ranked #4 on
Classification
on InDL
Large Scale Business Discovery from Street Level Imagery
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
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.
Ranked #3 on
Object Detection
on PASCAL VOC 2012
Rethinking the Inception Architecture for Computer Vision
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.
Ranked #8 on
Retinal OCT Disease Classification
on OCT2017
Batch Normalization: Accelerating Deep Network Training byReducing Internal Covariate Shift
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.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
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.
Training Deep Neural Networks on Noisy Labels with Bootstrapping
On MNIST handwritten digits, we show that our model is robust to label corruption.
Explaining and Harnessing Adversarial Examples
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.
Ranked #45 on
Image Classification
on MNIST
Scalable, High-Quality Object Detection
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.
Going Deeper with Convolutions
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).
Intriguing properties of neural networks
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks.
DeepPose: Human Pose Estimation via Deep Neural Networks
We propose a method for human pose estimation based on Deep Neural Networks (DNNs).
Scalable Object Detection using Deep Neural Networks
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).
Deep Neural Networks for Object Detection
Deep Neural Networks (DNNs) have recently shown outstanding performance on the task of whole image classification.
