Slide 1

Slide 1 text

Melanie Warrick | Skymind | @nyghtowl Computer Vision Deep Learning with DL4J

Slide 2

Slide 2 text

@nyghtowl Machine Learning

Slide 3

Slide 3 text

No content

Slide 4

Slide 4 text

@nyghtowl

Slide 5

Slide 5 text

@nyghtowl

Slide 6

Slide 6 text

@nyghtowl Artificial Neural Nets Input Output Hidden Run until error stops improving = converge Loss Function

Slide 7

Slide 7 text

@nyghtowl Computer Vision Who is it? Pixels Edges Object Parts Object Models Layer 2 Layer 3 Layer 4 Input

Slide 8

Slide 8 text

@nyghtowl Example: Image Captioning

Slide 9

Slide 9 text

Example: Image Generation

Slide 10

Slide 10 text

@nyghtowl Convolutional Neural Net

Slide 11

Slide 11 text

@nyghtowl Hadoop Spark AWS Skymind ND4J DeepLearning4J Native & JavaCPP & OpenMP & Cuda 7.5 Canova Data Neural Nets Linear Algebra LIBND4J C Backend

Slide 12

Slide 12 text

@nyghtowl Research References ● DL4J CNN Examples: https://github.com/deeplearning4j/ComputerVision-examples ● DL4J Examples: https://github.com/deeplearning4j/dl4j-0.4-examples ● CS231Convolution Neural Nets for Visual Recognition: https://cs231n.github.io/ ● Tiny ImageNet Classification with CNN: http://cs231n.stanford.edu/reports/leonyao_final.pdf ● AlexNet: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural- networks.pdf & https://github.com/BVLC/caffe/blob/master/models/bvlc_alexnet/train_val.prototxt ● Neural Networks and Deep Learning: http://neuralnetworksanddeeplearning.com/chap3.html ● Neuarl Networks: http://nbviewer.jupyter. org/github/masinoa/machine_learning/blob/master/04_Neural_Networks.ipynb ● Visual Information Theory: https://colah.github.io/posts/2015-09-Visual-Information/ ● Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift: http: //jmlr.org/proceedings/papers/v37/ioffe15.pdf ● Deep Learning Book: http://www.deeplearningbook.org/ ● Neural Networks for Machine Learning: https://www.coursera.org/course/neuralnets

Slide 13

Slide 13 text

@nyghtowl Image References ● U.S. Fish and Wildlife Service (animal sample dataset): http://digitalmedia.fws.gov/cdm/ ● http://www.dailytech. com/ExSiri+CEO+Poaches+Apple+to+Create+Viv+The+Global+Brain/article36387.htm ● http://3.bp.blogspot.com/- mMPT3tgVWaQ/U5qVs64HbRI/AAAAAAAAJCM/lEE4OiJmRSY/s1600/thumb-down-smiley.png ● http://4.bp.blogspot.com/-pUoO5oOuzOc/VcomU6qKT4I/AAAAAAAAAsg/TonkgL1iEjE/s1600/Screen% 2BShot%2B2015-08-11%2Bat%2B9.43.21%2BAM.png ● http://www.ucreative.com/inspiration/interesting-patterns-and-fractals-from-nature/ ● http://i.telegraph.co.uk/multimedia/archive/02122/WILLIAM-SHAKESPEAR_2122089b.jpg ● https://karpathy.github.io/2015/05/21/rnn-effectiveness/ ● https://pbs.twimg.com/media/CJm9HmfVEAEXU0c.jpg:large ● http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/ ● http://i.dailymail.co.uk/i/pix/2016/03/09/09/320583D500000578-3483569- Google_has_confirmed_its_AlphaGo_computer_has_taken_the_first_vi-a-11_1457516282972.jpg ● http://www.forensicmag.com/article/2016/02/autonomous-drones-fly-search-and-rescue-operations

Slide 14

Slide 14 text

@nyghtowl Computer Vision DL with DL4J Melanie Warrick skymind.io @nyghtowl gitter.im/deeplearning4j