scispace - formally typeset
Search or ask a question
Author

Dario Amodei

Bio: Dario Amodei is an academic researcher from Baidu. The author has contributed to research in topics: Computer science & Language model. The author has an hindex of 34, co-authored 49 publications receiving 13108 citations. Previous affiliations of Dario Amodei include OpenAI & Princeton University.


Papers
More filters
Proceedings Article
28 May 2020
TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
Abstract: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.

10,132 citations

Journal ArticleDOI
TL;DR: The ProteoWizard Toolkit is developed, a robust set of open-source, software libraries and applications designed to facilitate proteomics research that implements the first-ever, non-commercial, unified data access interface for proteomics, bridging field-standard open formats and all common vendor formats.
Abstract: Mass-spectrometry-based proteomics has become an important component of biological research. Numerous proteomics methods have been developed to identify and quantify the proteins in biological and clinical samples1, identify pathways affected by endogenous and exogenous perturbations2, and characterize protein complexes3. Despite successes, the interpretation of vast proteomics datasets remains a challenge. There have been several calls for improvements and standardization of proteomics data analysis frameworks, as well as for an application-programming interface for proteomics data access4,5. In response, we have developed the ProteoWizard Toolkit, a robust set of open-source, software libraries and applications designed to facilitate proteomics research. The libraries implement the first-ever, non-commercial, unified data access interface for proteomics, bridging field-standard open formats and all common vendor formats. In addition, diverse software classes enable rapid development of vendor-agnostic proteomics software. Additionally, ProteoWizard projects and applications, building upon the core libraries, are becoming standard tools for enabling significant proteomics inquiries.

2,480 citations

18 Feb 2016
TL;DR: It is shown that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech-two vastly different languages, and is competitive with the transcription of human workers when benchmarked on standard datasets.
Abstract: We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech-two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, enabling experiments that previously took weeks to now run in days. This allows us to iterate more quickly to identify superior architectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center, we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

1,973 citations

Posted Content
TL;DR: This article showed that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.
Abstract: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.

1,886 citations

Posted Content
TL;DR: A list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function, an objective function that is too expensive to evaluate frequently, or undesirable behavior during the learning process, are presented.
Abstract: Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society. In this paper we discuss one such potential impact: the problem of accidents in machine learning systems, defined as unintended and harmful behavior that may emerge from poor design of real-world AI systems. We present a list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function ("avoiding side effects" and "avoiding reward hacking"), an objective function that is too expensive to evaluate frequently ("scalable supervision"), or undesirable behavior during the learning process ("safe exploration" and "distributional shift"). We review previous work in these areas as well as suggesting research directions with a focus on relevance to cutting-edge AI systems. Finally, we consider the high-level question of how to think most productively about the safety of forward-looking applications of AI.

1,569 citations


Cited by
More filters
Posted Content
TL;DR: Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
Abstract: While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

12,690 citations

Proceedings Article
28 May 2020
TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
Abstract: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.

10,132 citations

01 Aug 2000
TL;DR: Assessment of medical technology in the context of commercialization with Bioentrepreneur course, which addresses many issues unique to biomedical products.
Abstract: BIOE 402. Medical Technology Assessment. 2 or 3 hours. Bioentrepreneur course. Assessment of medical technology in the context of commercialization. Objectives, competition, market share, funding, pricing, manufacturing, growth, and intellectual property; many issues unique to biomedical products. Course Information: 2 undergraduate hours. 3 graduate hours. Prerequisite(s): Junior standing or above and consent of the instructor.

4,833 citations

Posted Content
TL;DR: In this paper, layer normalization is applied to recurrent neural networks by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case.
Abstract: Training state-of-the-art, deep neural networks is computationally expensive One way to reduce the training time is to normalize the activities of the neurons A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute a mean and variance which are then used to normalize the summed input to that neuron on each training case This significantly reduces the training time in feed-forward neural networks However, the effect of batch normalization is dependent on the mini-batch size and it is not obvious how to apply it to recurrent neural networks In this paper, we transpose batch normalization into layer normalization by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case Like batch normalization, we also give each neuron its own adaptive bias and gain which are applied after the normalization but before the non-linearity Unlike batch normalization, layer normalization performs exactly the same computation at training and test times It is also straightforward to apply to recurrent neural networks by computing the normalization statistics separately at each time step Layer normalization is very effective at stabilizing the hidden state dynamics in recurrent networks Empirically, we show that layer normalization can substantially reduce the training time compared with previously published techniques

3,780 citations

Journal ArticleDOI
TL;DR: A broad survey of the recent advances in convolutional neural networks can be found in this article, where the authors discuss the improvements of CNN on different aspects, namely, layer design, activation function, loss function, regularization, optimization and fast computation.

3,125 citations