I received my phd from stanford, where i worked with feifei li. Stanford convolutional neural networks for visual recognition. Feifei li speaks at the 2017 grace hopper celebration ghc 17 on the importance of algorithms in the fields of artificial intelligence and machine learning. Feb 26, 20 a profile of bbc learning english producer, feifei. Feifei li, ranjay krishna, danfei xu lecture 6 2 april 23, 2020 administrative assignment 1 was due yesterday. I am currently a graduate student at stanford university, pursuing a masters in computer science. An introduction to deep neural networks for computer. Im broadly interested in computer vision and machine learning. Split data into folds, try each fold as validation and average the results fold 1 fold 2 fold 3 fold 4 fold 5 test fold 1 fold 2 fold 3 fold 4 fold 5 test.
I am a member of the stanford program in aiassisted care pac, which is a collaboration between the stanford ai lab and stanford clinical excellence research center that aims to use computer vision and machine learning to create aiassisted smart healthcare spaces. Aug 11, 2017 lecture 1 introduction to convolutional neural networks for visual recognition. She is a professor at stanford university and the codirector of stanfords humancentered ai institute and the stanford vision and learning lab. If you also have a dl reading list, please share it with me.
Methods and applications li deng and dong yu deep learning methods and applications li deng and dong yu deep learning. Methods and applications provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. Related work this work is inspired by previous work in both deep learning and speech recognition. Recent developments in neural network aka deep learning approaches have greatly advanced the performance of these stateoftheart visual recognition systems. Timnit gebru, jonathan krause, yilun wang, duyun chen, jia deng, erez lieberman aiden, li feifei. I am working in the stanford vision and learning lab, advised by prof. Feifei professor director, stanford ai lab computer science department office. Deep learning is one of the most highly sought after skills in ai. Feifei li, the internationally acclaimed scientist, speaks to cnbc about the vast opportunities as well as the perils of artificial intelligence in our future. Input is partitioned into nonoverlapping patches and. Endtoend speech recognition in english and mandarin 2. Lecture 1 introduction to convolutional neural networks for visual recognition. Director of ai at tesla, where i lead the team responsible for all neural networks on the autopilot.
Lecture 1 introduction to convolutional neural networks for. Deep learning for healthcare decision making with emrs. Learning datadriven curriculum for very deep neural networks on corrupted labels lu jiang, zhengyuan zhou, thomas leung, jia li. This course is inspired by stanford stats 385, theories of deep learning, taught by prof. The stanford course on deep learning for computer vision is perhaps the most widely. Deep learning pioneer feifei li on the fundamentals of. Targetdriven visual navigation in indoor scenes using deep. My research involves visual reasoning, vision and language, image generation, and 3d reasoning using deep neural networks. Sep 16, 2016 we show that our proposed method 1 converges faster than the stateoftheart deep reinforcement learning methods, 2 generalizes across targets and across scenes, 3 generalizes to a real robot scenario with a small amount of finetuning although the model is trained in simulation, 4 is endtoend trainable and does not need feature. The networks learn to reconstruct hidden information in an encoded image despite the presence of gaussian blurring, pixelwise dropout, cropping, and jpeg compression. Feifei li s research interests are in database systems and largescale data mangement. Deep learning provides a platform to solve identification and diagnostic problems arising in medicine and can be used in healthcare biometrics to analyze clinical parameters and their combinations. Deep visualsemantic alignments for generating image descriptions. When a very young child looks at a picture, she can identify simple elements.
Deep learning pioneer feifei li on the fundamentals of ethical ai. The general idea is that the rendered images of the physics engine are streamed to the deep learning framework, and the deep learning framework issues a control command based on the visual input and sends it back to the agent in the physics engine. Feifei li, ranjay krishna, danfei xu lecture 6 1 april 23, 2020 lecture 6. In a thrilling talk, computer vision expert feifei li describes the state of the art including the database of 15 million photos her team built to teach a computer to understand pictures and the key insights yet to come. Irv biederman, russell epstein, feifei li, aude oliva, bruno olshausen, simon thorpe.
Convolutional neural networks for visual recognition course by prof feifei li of stanford. Her main research interest is in vision, particularly highlevel visual recognition. There are many resources out there, i have tried to not make a long list of them. Neural network aka deep learning class on image classification. Imagenet large scale visual recognition challenge pdf. Animesh garg postdoc garg at cs dot stanford dot edu.
Ai luminary feifei li was among a group of distinguished ai researchers asked to talk about how to develop ethical ai programs. Deep visualsemantic alignments for generating image. Feifei li is an assistant professor at the computer science department, stanford university. Ensure your research is discoverable on semantic scholar. Modeldriven deep learning for physical layer communications hengtao he, shi jin, chaokai wen, feifei gao, geoffrey ye li, and zongben xu abstract intelligent communication is gradually becoming a mainstream direction. Our study on using deep learning techniques to perform sentiment analysis over geotagged tweets for analyzing and predicting this. Lecture 8 deep learning software tutorial of cs231n. Now, computers are getting smart enough to do that too. Claiming your author page allows you to personalize the information displayed and manage publications all current information on this profile has been aggregated automatically from publisher and metadata sources. Li has published more than 200 scientific articles in. She served as the director of the stanford artificial. Convolutional networks for visual recognition this spring. How we teach computers to understand pictures fei fei li.
Li works on ai, machine learning, computer vision, cognitive neuroscience and. Jiren zhu, russell kaplan, justin johnson, li feifei download pdf. In this course, you will learn the foundations of deep learning, understand how to build neural networks, and learn how to lead successful machine learning projects. Mar 23, 2015 how we teach computers to understand pictures fei fei li.
The course is taught by feifei li, a famous computer vision. Deep learning 2015, yann lecun, yoshua bengio and geoffrey hinton deep learning in neural networks. This lecture collection is a deep dive into details of the deep learning architectures with a focus on learning endtoend models for these tasks, particularly image classification. Feifei li is a chineseborn american computer scientist, nonprofit executive, and writer. Our study on using deep learning techniques to perform sentiment analysis over geotagged tweets for analyzing and predicting this years presidential election is covered by salt lake tribune and deseret news. This page has been archived and is no longer updated. I would be teaching courses on industrial relations at a. The stanford artificial intelligence laboratory sail has been a center of excellence for artificial intelligence research, teaching, theory, and practice since its founding in 1962. In the past she has also worked on cognitive and computational neuroscience. Lecture 1 introduction to convolutional neural networks. In computer vision, feifeis interests span from object and natural scene categorization to human activity categorizations in both videos and still images. Previously, i was a research scientist at openai working on deep learning in computer vision, generative modeling and reinforcement learning.
This course is a deep dive into details of the deep learning architectures with a focus on learning endtoend models for these tasks, particularly image classification. Lecture 8 deep learning software video lecture by prof feifei li. She is a professor of computer science at stanford university and the codirector of stanfords humancentered ai institute and the stanford vision and learning lab. Our most advanced machines are like toddlers when it comes to sight, li says. Careful observation, diverse viewpoints and the understanding that ai, for the moment, is an artifact of human biases are key. As a major branch of machine learning, deep learning dl has been applied in physical layer communications and demonstrated. Modeldriven deep learning for physical layer communications. Lu jiang, zhengyuan zhou, thomas leung, jia li, feifei li. Mar 17, 2015 feifei li, the director of stanfords artificial intelligence lab and vision lab, has spent the past 15 years teaching machines how to see.