Deep Learning OCR using TensorFlow and Python

In this post, deep learning neural networks are applied to the problem of optical character recognition (OCR) using Python and TensorFlow. This post makes use of TensorFlow and the convolutional neural network class available in the TFANN module. The full source code from this post is available here. Introduction to OCR OCR is the transformation […]

Continue reading


NVIDIA GTC China: TensorRT 3.0, AI Machine Processor Xavier, and China Partnerships

The annual NVIDIA GTA Conference opened in Beijing on September 26th. The much-anticipated GPU developers’ conference showcased the company’s latest endeavours in AI, deep learning, healthcare, VR, and self-driving cars. In addition to deep learning engine TensorRT 3.0, NVIDIA introduced the HGX-1 hyperscale GPU accelerator powered by Tesla V100 for AI cloud computing, and the […]

Continue reading


RIP Theano

Before TensorFlow, PyTorch and Caffe; Theano was the major library for deep learning development. However, the library’s development and support will end after the upcoming Theano 1.0 release. The news came in an email from Theano’s main developer Pascal Lamblin and Yoshua Bengio, notable expert on artificial neural networks and deep learning. “We will continue […]

Continue reading


Huawei Announces Kirin 970: AI In Your Phone

China’s biggest domestic mobile phone maker, Huawei, is now powering its phones with artificial intelligence (AI) engines. The Chinese tech giant today unveiled Kirin 970 — a SoC (system on a chip) for mobile phones — at IFA (Internationale Funkausstellung Berlin), one of the oldest industrial exhibitions in Germany. The chipset is powered by HiAI, […]

Continue reading


Softmax Regression using TensorFlow

Note: This article has also featured on geeksforgeeks.org . This article discusses the basics of Softmax Regression and its implementation in Python using TensorFlow library. What is Softmax Regression? Softmax regression (or multinomial logistic regression) is a generalization of logistic regression to the case where we want to handle multiple classes. A gentle introduction to […]

Continue reading


Introduction to TensorFlow

Note: This article has also featured on geeksforgeeks.org . This article is a brief introduction to TensorFlow library using Python programming language. Introduction TensorFlow is an open-source software library. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google’s Machine Intelligence research organization for the purposes of conducting machine […]

Continue reading


Calibrating a Projection Matrix for Path of Exile

This post is part of a series on creating a bot for the game Path of Exile © (PoE). In this post, techniques for updating the internal representation of the world given a static image of the game are explored. A difficulty involved in having a robot interact with visual input, is that image data […]

Continue reading


How to install NVIDIA CUDA 8.0, cuDNN 5.1, Tensorflow, and Keras on Ubuntu 16.04

Please follow the instructions below and you will be rewarded with Keras with Tenserflow backend and, most importantly, GPU support. Step 1. Linux Update apt repositories and install the linux -image-extra-virtual package. This package includes the kernel module that’s required by the NVIDIA drivers. sudo apt-get update sudo apt-get install -y linux-image-extra-virtual Install the version of the headers that matches the freshly installed […]

Continue reading


Tensorflow Programs and Tutorials

This repository did some toy experiments based on Tensorflow (a popular machine learning framework), in order to introduce some deep learning concepts which are used for image recognition and language modeling. I summarized them into three parts, they are: Convolutional Neural Network for handwritten digits recognition LSTM-based character level sequence to sequence generation Question pair […]

Continue reading


Deep Learning with Dynamic Computation Graphs

ABSTRACT Batch processing of dynamic graphs is a very common technique for a variety of applications, such as computer vision and natural language processing. However, due to the varieties of type and shapes between distinct data, batch processing with a static graph over such dataset is almost impossible with current frameworks and libraries. In this […]

Continue reading