- Popular Deep Learning Tools – a review - Jun 18, 2015.
Deep Learning is the hottest trend now in AI and Machine Learning. We review the popular software for Deep Learning, including Caffe, Cuda-convnet, Deeplearning4j, Pylearn2, Theano, and Torch.
- Dark Knowledge Distilled from Neural Network - May 26, 2015.
Geoff Hinton never stopped generating new ideas. This post is a review of his research on “dark knowledge”. What’s that supposed to mean?
- Talking Machine – Deep Learning in Speech Recognition - May 2, 2015.
A summary about an episode on the talking machine about deep neural networks in speech recognition given by George Dahl, who is one of Geoffrey Hinton’s students and just defended his Ph.D last month.
- Watson Developer Cloud-Visual Recognition - Apr 3, 2015.
IBM Bluemix is a cloud platform which offers both Platform as a Service and Mobile Backend as a Service. Its services include Speech to Text, Text to Speech, Visual Recognition, Concept Insights, and Tradeoff Analytics.
- Talking Machine – 3 Deep Learning Gurus Talk about History and Future, part 2 - Mar 26, 2015.
Key ideas from a podcast with Deep Learning gurus Geoff Hinton, Yoshua Bengio, and Yann LeCun, where they explain the power of distributed representation and also propose a new open paper review process.
- Talking Machine – 3 Deep Learning Gurus Talk about History and Future of Machine Learning, part 1 - Mar 25, 2015.
An recent interview from the talking machine podcast with three deep learning experts. They talked about the neural network winter and its renewal.
- Facebook Open Sources deep-learning modules for Torch - Feb 9, 2015.
We review Facebook recently released Torch module for Deep Learning, which helps researchers train large scale convolutional neural networks for image recognition, natural language processing and other AI applications.
- Deep Learning can be easily fooled - Jan 14, 2015.
It is almost impossible for human eyes to label the images below to be anything but abstract arts. However, researchers found that Deep Neural Network will label them to be familiar objects with 99.99% confidence. The generality of DNN is questioned again.
- GDELT: Big Data of News, Conflicts, and Society - Sep 29, 2014.
What is happening in this world today? Obviously, it is impossible for us to read and analyze billions of news reports published every day. GDELT is designed to record, analyze, visualize and even forecast our planet.
- IBM Watson’s Next Step: Partnership with Universities - Aug 15, 2014.
Students from ten top tech universities now have access to Watson. For students at New York University interested in Watson, Capstone Project Course would be their first choice.
- OpenML: Share, Discover and Do Machine Learning - Aug 11, 2014.
OpenML is designed to share, organize and reuse data, code and experiments, so that scientists can make discoveries more efficiently. It is an interesting idea to build a network of machine learning.
- When Watson Meets Machine Learning - Jul 2, 2014.
Our report on a recent Cognitive Systems meetup co-sponsored by IBM Watson and NYU Center for Data Science, IBM Watson Ecosystem, and machine learning applications, from healthcare to cognitive toys. You will want Fang!
- NYU Data Science Program – Things to Know Part 2 - Jun 16, 2014.
NYU Data Science program reviewed from inside, including courses on Machine Learning, Big Data, Deep Learning, top professors, great NYC location, and future plans.
- NYU Data Science Program – Things to Know - Jun 13, 2014.
Inside summary of NYU Data Science program launched last year, what it is, and what makes it special.