Convolutional neural networks for visual recognition. Feifei li ai luminary feifei li was among a group of distinguished ai researchers asked to share their thoughts on how to develop ethical ai. Deep learning has been successfully introduced to collaborative filtering for recommendation systems in recent years. Learning deep architectures for ai by yoshua bengio contains an indepth tutorial on learning rbms. Lance downing, william beninati, terry platchek, arnold milstein, li feifei.
Feifei li on ai and machine learning the engineering of. When ai researchers started using imagenet to train neural networks to catalog photos sail faculty working in machine learning, deep learning, big data, knowledge base, and logic include. Lecture 8 deep learning software video lecture by prof. Feifei li s main research areas are in machine learning, deep learning, computer vision and cognitive and computational neuroscience. The course is taught by feifei li, a famous computer vision. When a very young child looks at a picture, she can identify simple elements. Previously, i was a research scientist at openai working on deep learning in. D advances in deep neural networks judea pearl, michael. Its the oldest advice in all the books in philosophies is know yourself. Li s main research areas are in machine learning, deep learning, computer vision and cognitive and computational neuroscience. Cs231n convolutional neural networks for visual recognition. Feifei li s research interests are in database systems and largescale data mangement.
Course materials and notes for stanford class cs231n. Deep learning pioneer feifei li on the fundamentals of. 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. A introductory book on deep learning methods and applications from microsoft research for signal and information processing tasks. It easy it is l 12th, the goddess of deep learning fei. Lecture 1 introduction to convolutional neural networks.
I would be teaching courses on industrial relations at a. Googles feifei li 0 comment ann rosenberg, feifei li, finale doshivelez, janet george, julie yoo, megan price, miriah meyer. Short course on deep learning resources cvit, iiit hyderabad. Computer vision, from 3d reconstruction to recognition. A deep learning tutorial from lisa lab, university of montreal. A quest for visual intelligence in computers feifei li. Feifei li is a professor in the computer science department at stanford university, and codirector of stanfords upcoming humancentered ai institute. Convnetjs, recurrentjs, reinforcejs, tsnejs because i. The autonomous learning library is a deep reinforcement learning library for pytorch that i have been working on for the last year or so. Feifei li, professor of computer science at stanford university. Lecture 1 introduction to convolutional neural networks for.
At the new stanford institute for humancentered artificial intelligence, which specializes in research and education on the potential uses of machine learning. Our most advanced machines are like toddlers when it comes to sight, li says. The online version of the book is now complete and will remain available online for free. How can machine learningespecially deep neural networksmake a real difference selection from deep learning book. Midterm grades released last night, see piazza for more information and statistics. Deep learning reading list university of melbourne. Resources for deep reinforcement learning yuxi li medium. Irv biederman, russell epstein, feifei li, aude oliva, bruno olshausen, simon thorpe. I am working in the stanford vision and learning lab, advised by prof. This lecture collection is a deep dive into details of the deep learning architectures with a focus on.
View feifei lis profile on linkedin, the worlds largest professional community. Now, computers are getting smart enough to do that too. We are tackling fundamental open problems in computer vision research and are intrigued by visual functionalities that give rise to. See the complete profile on linkedin and discover feifeis. A glossary of technical terms and commonly used acronyms in the intersection of deep learning and nlp is also provided. Convolutional neural networks for visual recognition by feifei li, andrej karpathy and justin johnson, 2016.
Intel dives into ai, facebook brings neural networks to your. Attentive and collaborative deep learning for recommendation. The purpose of the dialogue was to discuss the impact of artificial intelligence on the future of mankind. The following is a list of free or paid online courses on machine learning, statistics, datamining, etc. I received my phd from stanford, where i worked with feifei li on convolutionalrecurrent neural network architectures and their applications in computer vision, natural language processing and their.
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. Apr 18, 2017 written by three experts in the field, deep learning is the only comprehensive book on the subject. A read is counted each time someone views a publication summary such as the title, abstract, and list of authors, clicks on a figure, or views or downloads the fulltext. Li works on ai, machine learning, computer vision, cognitive neuroscience and computational neuroscience. Stanford convolutional neural networks for visual recognition. The deep learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular.
I developed a number of deep learning libraries in javascript e. Recent developments in neural network aka deep learning approaches have greatly advanced the. 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. Deep learning by yoshua bengio, ian goodfellow, and aaron courville is an advanced textbook with good coverage of deep learning and a brief introduction to machine learning. Feifei li grew up in chengdu, an industrial city in southern china. The book appeals to advanced undergraduate and graduate students, postdoctoral researchers, lecturers and industrial researchers, as well as anyone interested in deep learning and natural language processing. She served as the director of stanfords ai lab from 20 to 2018. Feifei li assistant attending physicist memorial sloan. Deep learning systems are, as li says, bias in, bias out. Distributed trajectory similarity search, project website, talk, poster by d. How feifei li will make artificial intelligence better for humanity. My research has been broadly in the areas of computer vision, machine learning, and deep learning, with particular focus on human activity and video understanding, and applications to healthcare. May 28, 2019 deep learning pioneer feifei li on the fundamentals of ethical ai evaluate techtarget photo.
One of the top minds in artificial intelligence, li is cocreator of imagenet, a visual object recognition database which heralded the beginning of the deep learning revolution. Our study on using deep learning techniques to perform sentiment analysis over geotagged tweets for analyzing and predicting this. She is a professor at stanford university and the codirector of stanfords humancentered ai institute and the stanford vision and learning lab. Michael nielsens neural networks and deep learning online book. Andrej karpathy academic website stanford computer science. 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. Lecture 1 introduction to convolutional neural networks for visual recognition. Feifei li is professor of computer science at stanford university, and director of the stanford artificial intelligence lab sail. Srikumar in proceedings of 24th acm conference on computer and communications security ccs 2017, pages 12851298, november 2017. Our list of deep learning researchers and industry leaders are the people you should follow to stay current with this wildly expanding field in ai. In the past she has also worked on cognitive and computational neuroscience. Anomaly detection and diagnosis from system logs through deep learning, talk, by m. Deep learning pioneer feifei li on the fundamentals of ethical ai ai luminary feifei li was among a group of distinguished ai researchers asked to share their thoughts on how to develop ethical ai. Nicholas thompson, editor in chief of wired, moderated the 90minute conversation in the packed memorial auditorium, filled to its 1705seat capacity the purpose was to discuss how ai will affect our future.
Feifei li on ai and machine learning ricks cafe ai. She was a lonely, brainy kid, as well as an avid reader. Intel dives into ai, facebook brings neural networks to. Shes always done such great work, and i loved cs231n. The deep learning textbook can now be ordered on amazon. Im good with karpathy earning 1 mil although interestingly, the kinds of scientists who can make 1 mil usually weight comp very.
Feifei professor director, stanford ai lab computer science department office. The american dream, the goddess of deep learning feifei li. Imagenet enabled deep learning to go bigits at the root of. Feb 26, 20 a profile of bbc learning english producer, feifei. How feifei li will make artificial intelligence better. Lecture 1 introduction to convolutional neural networks for visual. The goal was to go beyond current libraries by providing components for building and testing new agents. Nearly all of the faculty members doing work in ml and pretty much all of those involved in deep learning. 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.
F eifei li, the internationallycelebrated scientist, has always been a champion of the positive power of artificial intelligence a. Targetdriven visual navigation in indoor scenes using deep. Two major artificial intelligence experts, yuval hralili and li feifei, started a conversation of 90 minutes. Prior to that, she was on faculty at princeton university 20072009 and university of illinois urbanachampaign 20052006. Melinda gates and feifei li want to liberate ai from. What does it mean to live in a world in which you learn about something so important about yourself from an algorithm. 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. Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reshape the future of artificial. She joined stanford in 2009 as an assistant professor. Feifei li 4 12 deep learning researchers and leaders sep 23, 2019. Recent developments in neural network aka deep learning approaches have greatly advanced the performance of these stateoftheart visual recognition systems. Aug 11, 2017 lecture 1 introduction to convolutional neural networks for visual recognition. Yuval noah harari and feifei li on artificial intelligence. Feifei li is a chineseborn american computer scientist, nonprofit executive, and writer.
Our list of deep learning researchers and industry leaders are the people you should. This page has been archived and is no longer updated. Previously, i was a research scientist at openai working on deep learning in computer vision, generative modeling and reinforcement learning. The stanford vision and learning lab svl at stanford is directed by professors feifei li, juan carlos niebles, and silvio savarese. She is the inventor of imagenet and the imagenet challenge, a critical largescale dataset and benchmarking effort that has contributed to the latest developments in deep learning. Working in areas of computer vision and cognitive neuroscience, feifei builds smart algorithms that enable computers and robots to see and think, inspired by the way the human brain works in the real world. In these studies, autoencoder models are usually used to extract latent features of items or users, and related researches facilitate the learning techniques using item and user latent factors in matrix factorization models. An introduction to the concepts and applications in computer vision. She was the founding director of the recently established stanford toyota center for humancentric ai research in 20152016. Li recognized that while the algorithms that drive artificial intelligence may appear to. Feifei li, the internationally acclaimed scientist, speaks to cnbc about the vast opportunities as well as the perils of artificial intelligence in our future. Unsupervised visuallinguistic reference resolution in instructional videos. Deep learning for healthcare decision making with emrs.
Melinda gates and feifei li want to liberate ai from guys with hoodies. Feifei lis research works university of utah, utah uou. Feifei lis main research areas are in machine learning, deep learning, computer vision and cognitive and computational neuroscience. Feifei li is also a leading female engineer in the field of machine learning, which has recently led the new technology trend. The discussion jumped into the deep, difficult topic of free will and. Although interest in machine learning has reached a high point, lofty expectations often scuttle projects before they get very far. This is a collection of resources for deep reinforcement learning, including the following sections. The class was the first deep learning course offering at stanford and has grown from 150 enrolled in 2015 to 330 students in 2016, and 750 students in 2017. Mar 23, 2015 when a very young child looks at a picture, she can identify simple elements. Artificial intelligence columbia university free machine learning columbia university free machine learning stanford university free neural networks for machine learning university of toronto free. Animesh garg postdoc garg at cs dot stanford dot edu. A text book on deep learning written by ian goodfellow, yoshua bengio, and aaron courville. How we teach computers to understand pictures fei fei li. 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.
1062 718 92 1259 49 1407 727 817 1467 794 1407 89 1557 421 316 70 1402 125 96 1285 1000 43 451 1439 1097 893 1352 692 1279 685