how to use #TensorFlow in #Clojure
on 02017-05-09#image-processing content-aware fill of faces using #neural-networks; extended commentary on #Torch-7 vs. #TensorFlow
on 02017-03-02#deep-learning #neural-networks with #tensorflow for low-cost #robotics
on 02016-09-23#Tutorial on #TensorFlow #deep-learning to do #OCR of handwritten digits
on 02016-09-02Terry Broad (“Artist and research student in the Computing Department”) uses #DCGANs in #TensorFlow to generate simplified representations of Blade Runner frames and see what they look like. #GANs #art
on 02016-05-24Jeff Dean’s talk about #deep-learning in general and #TensorFlow on 2015-10-22, before its release. He explains how important #automatic-differentiation is to them and mentions Theano.
on 02016-01-11a brief comparison of #TensorFlow, Facebook’s Ronan Collobert’s faster #Torch-7, the Caffe convnets library, and Yoshua Bengio’s #Theano. “Just as a Tesla is yet another four-wheeled conveyance with four doors, a steering wheel and a roof, TensorFlow appears to be the best, most convenient library for #deep-learning, more worthy of anointment.”
on 02016-01-11#TensorFlow #performance #benchmarks
on 02015-11-11Jeff Dean talks about the #TensorFlow #machine-learning system as part of his keynote last week at BayLearn15 about machine learning.
on 02015-11-10the #tensorflow white #paper #pdf, describing its roots as a better replacement for DistBelief.
on 02015-11-09"TensorFlow" is a high-throughput #dataflow array computing library and IDE with built-in reverse-mode #automatic-differentiation for optimization, with Python and C++ APIs and #IPython integration. At this moment in history, the growth of computer power has made a bunch of important #DSP and statistical tasks just feasible, so we are seeing things like self-driving cars, superhuman image recognition, and so on. But it’s been very difficult to take advantage of the available computational power, because it’s in the form of GPUs and clusters. So this is designed to make it easy to do exactly these things, and to scale them with your available computing power, along with libraries of the latest tricks in neural networks, machine learning (which is pretty close to "statistics").
on 02015-11-09