Deep Learning Tutorials ě°˝€” DeepLearning v0.1 documentation Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. See these course notes for a brief introduction to Machine Learning for AI and an introduction to Deep Learning algorithms. Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. For more about deep learning algorithms, see for example: The tutorials presented here will introduce you to some of the most important deep learning algorithms and will also show you how to run them using Theano. The algorithm tutorials have some prerequisites. The code is available on the Deep Learning Tutorial repositories. The purely supervised learning algorithms are meant to be read in order: Building towards including the mcRBM model, we have a new tutorial on sampling from energy models: LSTM network for sentiment analysis:
Douglas Engelbart’s Unfinished Revolution Doug Engelbart knew that his obituaries would laud him as “Inventor of the Mouse.” I can see him smiling wistfully, ironically, at the thought. The mouse was such a small part of what Engelbart invented. We now live in a world where people edit text on screens, command computers by pointing and clicking, communicate via audio-video and screen-sharing, and use hyperlinks to navigate through knowledge—all ideas that Engelbart’s Augmentation Research Center at Stanford Research Institute (SRI) invented in the 1960s. To Engelbart, computers, interfaces, and networks were means to a more important end—amplifying human intelligence to help us survive in the world we’ve created. Engelbart’s vision for more capable humans, enabled by electronic computers, came to him in 1945, after reading inventor and wartime research director Vannevar Bush’s Atlantic Monthly article “As We May Think.” Engelbart’s failure to spread the less tangible parts of his vision stems from several circumstances.
Bayes' Theorem Bayes' Theorem for the curious and bewildered; an excruciatingly gentle introduction. Your friends and colleagues are talking about something called "Bayes' Theorem" or "Bayes' Rule", or something called Bayesian reasoning. They sound really enthusiastic about it, too, so you google and find a webpage about Bayes' Theorem and... It's this equation. So you came here. Why does a mathematical concept generate this strange enthusiasm in its students? Soon you will know. While there are a few existing online explanations of Bayes' Theorem, my experience with trying to introduce people to Bayesian reasoning is that the existing online explanations are too abstract. Or so they claim. And let's begin. Here's a story problem about a situation that doctors often encounter: 1% of women at age forty who participate in routine screening have breast cancer. 80% of women with breast cancer will get positive mammographies. 9.6% of women without breast cancer will also get positive mammographies.
A few words on Doug Engelbart Bret Victor / July 3, 2013 Doug Engelbart died today. His work has always been very difficult for writers to interpret and explain. Technology writers, in particular, tend to miss the point miserably, because they see everything as a technology problem. Here's the most facile interpretation of Engelbart, splendidly exhibited by this New York Times headline: Douglas C. This is as if you found the person who invented writing, and credited them for inventing the pencil. Then there's the shopping list interpretation: His system, called NLS, showed actual instances of, or precursors to, hypertext, shared screen collaboration, multiple windows, on-screen video teleconferencing, and the mouse as an input device. These are not true statements. Engelbart had an intent, a goal, a mission. The problem with saying that Engelbart "invented hypertext", or "invented video conferencing", is that you are attempting to make sense of the past using references to the present. Here's an example. "Ah!" "Ah!" No.
Can Creativity be Automated? In 2004, New Zealander Ben Novak was just a guy with a couple of guitars and distant dreams of becoming a pop star. A year later one of Novak’s songs, “Turn Your Car Around,” had invaded Europe’s radio stations, becoming a top-10 hit. Novak had to beat long odds to get discovered. The process record labels use to find new talent—A&R, for “artists and repertoire”—is fickle and hard to explain; it rarely admits unknowns like him. So Novak got into the music business through a back door that had been opened not by a human, but by an algorithm tasked with finding hit songs. It’s widely accepted that creativity can’t be copied by machines. But now we’re learning that for some creative work, that simply isn’t true. The algorithm that kindled Novak’s music career belongs to Music X-Ray, whose founder, Mike McCready, has spent the last 10 years developing technology to detect musical hooks that are destined for the charts. Why, yes. Algorithms won’t only do work that requires a critical eye.
The Psychology of Collaboration - Dr Irene Greif for Technology Review As part of their series on collaboration, Jodi from Technology Review interviewed Irene Greif at IBM about the psychology of collaboration. The focus of the interview was about the non-technology aspects of collaboration, and they discussed: - Too much automation leads to process breakdowns. The system can't see what people can see. - More informal interaction in the office is now online, meaning that combining informal and formal things may be more possible. - Knowledge management failed; social software does knowledge management as part of work. - Dogear gave better search results on the IBM intranet than intranet search. - Why collaboration requires the sharing of pre-finished thinking and artifacts. The most interesting comment to me from Irene was this: "Jodi: What qualities will make or break the next big thing in collaboration? My Comments 1. 2. 3. 4. 5.
The Psychology of Collaboration In the 1980s, long before the rise of online social networks, Irene Greif helped found the field of computer-supported coöperative work (CSCW), which explores how technology helps people collaborate. Today Greif is an IBM fellow, the company’s highest technical honor, and director of collaborative user experience in IBM Research. Jodi Slater, who worked with Greif at Lotus Development after it was bought by IBM in the 1990s and later cofounded the business consultancy MarketspaceNext, recently spoke with Greif for Technology Review about why some of the hardest collaboration problems have nothing to do with technology. TR: How are today’s technologies that help employees collaborate different from those that existed before, such as Lotus Notes? Greif: What got researchers interested in starting this field [CSCW] was that anthropologists went into offices and started seeing the kinds of things that break when you automate too much. How has this played out in IBM?