Deep Learningでヒアリを検出・判定する(YOLO9000) - algonote
“殺人アリ"ことヒアリが日本に上陸したらしい。 Twitterではヒアリかどうかを判別してくれるヒアリ警察が人気だが、画像認識ではなく、中身は人間の専門家のようだ。ヒアリ警察さんも24時間365日稼働できないと思うので、Deep Learningで実装できないのか模索してみる。 先行事例 IBM Watsonはデフォルトでfire ant(ヒアリ)に対応。 dotnsf.blog.jp ただ、ヒアリ警察さんで紹介されている代表画像をかませてみたところ、全てのアリを識別できるわけではなかった。 アリのデータセットAntWebというのもあるらしい upura.hatenablog.com サイトのつくりが少し見辛い。 ざっとみた感じあくまで掲載論文のサーチが主眼のようなので、画像は少なめ。 IMAGENETにもfire antカテゴリあり Fire ant こちらは画像が豊富にある他、クモ等、
Deep Learning with Docker - Affine Layer
Docker is a way to statically link everything short of the Linux kernel into your application. Because you can access GPUs while using a Docker container, it's also a great way to link Tensorflow or any dependencies your machine learning code has so anyone can use your work. You can distribute a reproducible machine learning project that requires little to no setup on the part of the user, so inst
Perceptual Adversarial Networks for Image-to-Image Transformation
In this paper, we propose a principled Perceptual Adversarial Networks (PAN) for image-to-image transformation tasks. Unlike existing application-specific algorithms, PAN provides a generic framework of learning mapping relationship between paired images (Fig. 1), such as mapping a rainy image to its de-rained counterpart, object edges to its photo, semantic labels to a scenes image, etc. The prop
Google Announces Tensorflow Lite: A Neural Network Library for Mobile Phones
Moving Your Bugs Forward in Time: Language Trends That Help You Catch Your Bugs at Build Time Instead of Run Time Chris Price discusses the critical shift from catching bugs at runtime to identifying them during the build process. He explains how leveraging modern programming language features such as static typing in dynamic languages, null safety, immutable data structures, and exhaustive patter
Implementing Simple Classification using a Neural Network in Ruby - Practical Artificial Intelligence
Implementing Simple Classification using a Neural Network in Ruby In this blog post I will show how to use neural networks in Ruby to solve a simple classification problem. We will be using the RubyGem ruby-fann to help us setup a network, train and make predictions in a matter of minutes. For our dataset we will be using school admission data, this was also the dataset used for in our Implementi
YellowFin and the Art of Momentum Tuning
Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable. Recently researchers have shown renewed interest in simpler methods like momentum SGD as they may yield better test metrics. Motivated by this trend, we ask: can simp
Meow Generator
I experimented with generating faces of cats using Generative adversarial networks (GAN). I wanted to try DCGAN, WGAN and WGAN-GP in low and higher resolutions. I used the CAT dataset (yes this is a real thing!) for my training sample. This dataset has 10k pictures of cats. I centered the images on the kitty faces and I removed outliers (I did this from visual inspection, it took a couple of hours
Tips for Training Recurrent Neural Networks
Tips for Training Recurrent Neural Networks Some practical tricks for training recurrent neural networks: Optimization Setup Adaptive learning rate. We usually use adaptive optimizers such as Adam (Kingma14) because they can better handle the complex training dynamics of recurrent networks that plain gradient descent. Gradient clipping. Print or plot the gradient norm to see its usual range, then
Home - Ike-ON
Unlock Your Potential: Top 10 Reasons to Learn Python Python is one of the most popular programming languages in the world. As technology advances and more companies use Python … Read More C# course from scratch for beginners If you have only a general idea of what programming is and have never been professionally engaged in it, we recommend that you start learning from the very basics. Read More
A Tour of Recurrent Neural Network Algorithms for Deep Learning - MachineLearningMastery.com
As with all feed forward network paradigms, the issues are how to connect the input layer to the output layer, include feedback activations, and then train the construct to converge. Let’s now take a tour of the different types of recurrent neural networks, starting with very simple conceptions. Fully Recurrent Networks The layered topology of a multilayer Perceptron is preserved, but every elemen
Orthogonal Initialization in Convolutional Layers · Hendrik J. Weideman
Orthogonal Initialization in Convolutional Layers 12 Dec 2015 In Exact solutions to the nonlinear dynamics of learning in deep linear neural networks Saxe, McClelland, and Ganguli investigate the question of how to initialize the weights in deep neural networks by studying the learning dynamics of deep linear neural networks. In particular, they suggest that the weight matrix should be chosen as a
Google Brain、リカレントニューラルネットワークを使用した独自の音楽を生成する「Performance RNN」を発表。ピアニストの約1400の演奏を学習。音声あり
Google Brain、リカレントニューラルネットワークを使用した独自の音楽を生成する「Performance RNN」を発表。ピアニストの約1400の演奏を学習。音声あり 2017-07-01 人工知能について研究する機関Google Brainは、LSTMベースのリカレントニューラルネットワーク（Recurrent Neural Network）を使用して独自の音楽を生成する「Performance RNN」を発表しました。 生成した音楽はこちらです。既存の作品のパフォーマンスではありません。 このモデルは、実際のピアニストによる約1400の演奏のMIDIキャプチャを含む「Yamaha e-Piano Competition」データセットで訓練されました。 関連 Google Brain、落書きの続きをニューラルネットワークが推測して描いてくれるプロジェクト「sketch-rnn」を
Dropout as a Bayesian Approximation: Appendix
We show that a neural network with arbitrary depth and non-linearities, with dropout applied before every weight layer, is mathematically equivalent to an approximation to a well known Bayesian model. This interpretation might offer an explanation to some of dropout's key properties, such as its robustness to over-fitting. Our interpretation allows us to reason about uncertainty in deep learning,
3D Convolutional Neural Network input shape
I'm having a problem feeding a 3D CNN using Keras and Python to classify 3D shapes. I have a folder with some models in JSON format. I read those models into a Numpy Array. The models are 25*25*25 and represent the occupancy grid of the voxelized model (each position represents if the voxel in position (i,j,k) has points in it or no), so I only have 1 channel of input, like grayscale images in 2D
AMD ROCm™ Documentation — ROCm Documentation Home
ROCm Documentation is transitioning to this site. For the legacy documentation, please visit docs.amd.com. For more information or to provide feedback about this documentation transition, please see our announcement.
How to Visualize Your Recurrent Neural Network with Attention in Keras
Neural networks are taking over every part of our lives. In particular — thanks to deep learning — Siri can fetch you a taxi using your voice; and Google can enhance and organize your photos automagically. Here at Datalogue, we use deep learning to structurally and semantically understand data, allowing us to prepare it for use automatically. Neural networks are massively successful in the domain
How HBO’s Silicon Valley built “Not Hotdog” with mobile TensorFlow, Keras & React Native | HackerNoon
How HBO’s Silicon Valley built “Not Hotdog” with mobile TensorFlow, Keras & React Native Too Long; Didn't ReadThe <a href="http://www.hbo.com/silicon-valley">HBO show <em>Silicon Valley</em></a> released a real AI app that identifies hotdogs — and not hotdogs — like the one shown on season 4’s 4th episode (the app is <a href="https://www.seefoodtechnologies.com/nothotdog/">now available on Android
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
ディープラーニングとStreet ViewイメージによるGoogle Mapsの改善
Lua版 ゼロから作るDeep Learning まとめ - Qiita
Lua版 ゼロから作るDeep Learning その９［損失関数（バッチ対応版）］ - Qiita
