Posts
Numpy Gives functions for working with multidimensional arrays. Numpy arrays have 1)Rank 2)Shape (given by dim of vector) Numpy arrays can be created like: a=np.array([1,2,3],[2,3,4]) #with initialize a=np.zeros(2,2) / np.ones(2,2) / np.random.random(4,4)
Here I will show you how to implement a neural network for logistic regression from basics. What is logistic regression ? The two main types of problems in the machine learning are are classification and regression. Both techniques are used for prediction of labels for a given data set. In classification, data can be fitted into a different classes, hence the labels will give discrete values. For regression, the data set is mapped into continuous values. Different types of regression include linear regression, logistic regression etc. Here for one training example, the neural network using logistic regression is explained. If two features of a image is considered for training purpose , the linear combination of the features with weights and bias can be shown as below : Z = w1x1+w2x2+b The activation function selected for logistic regression here is sigmoid function. This shows the forward propagation step in neural net. Now the output of this neural net should be close to th...
Jupyter notebook allows you to work on different languages on a single paltform. Here We will see how to install jupyter using python commands. One of the advantage I have noticed in the notebook is that you don't have to keep all the required modules for your program in the system. You can just import it in the notebook itselg. For example, 'import numpy, will allow you to use the package directly from the notebook. How to use IPython Notebook or Jupiter Notebook First install ipython using the following command from shell : pip install ipython Next install Jupiter notebook as : pip install jupyter Open jupyter notebook from user (not from root) : jupyter notebook it showed some permission denied error like : IOError: [Errno 13] Permission denied: '/run/user/6138/jupyter/notebook_cookie_secret' I googled so much and the following fixed the code : Run the command below export XDG_RUNTIME_DIR="" Then again type jupyter notebook It will now open ...
Computer Vision APIs Different computer vision tools and APIs are : Google CV Watson VR Amazon R Microsoft CV Clarif.ai Cloudsight Scale https://www.scaleapi.com/image-annotation Imagga vize.ai https://vize.ai/ http://www.recognize.im/ Moodstocks ( http://www.moodstocks.com/pricing/ ) * Kooaba ( http://www.kooaba.com/en/plans_a... ) * IQ Engines ( https://www.iqengines.com/pricing/ ) * LTU technologies ( http://www.ltutech.com/ ) Camfind - Image recognition back-end for the popular app CamFind. Take advantage of the leading image recognition platform through an easy to use web API. Recognize API | Mashape - Vufind Recognize is a real-time image recognition API for classification and monetization of photos and videos. Recognize uses object recognition to uncover meaning and metadata of photos and videos for contextual image commerce and advertising. Kooaba - Our cloud-based image recognition solutions mak...
Computer Vision APIs Comparison (Facial Recognition) Different APIs are: Google CV ,Watson VR,Amazon R,Microsoft CV, Clarif.ai,Cloudsight,Scale,Imagga,vize.ai,Kooaba,IQ Engines,LTU technologies , Face Recognition,Face (Detection),Animetrics Face Recognition,Skybiometry Face Detection and Recognition,Face++,FaceMark,EmoVu by Eyeris Face and scene recognition by Rekognition.com,FaceRect,Betaface API,EyeFace,Kairos, TinEye API and list goes on… Comparison Google CV classifies images into thousands of categories (e.g., "sailboat", "lion", "Eiffel Tower"), detects individual and faces within images ,emotions, and finds and reads printed words contained within images. Uses tensorflow Face ++ Locate and return keypoints of face components, including face contour, eye, eyebrow, lip and nose contour. Face++ provides analysis with high-precision, most detailed landmarks with up to 106 ...
INTRODUCTION The main goal of Question Answering system is to process requests in natural language form and to provide the accurate short answers to them. Most of the web Browsers we are using today handles QA tasks as information retrieval. So instead of retrieving the precise answers we get all documents similar to our query. Rather than keyword based queries natural language expressions would be processed by efficient QA systems. Mainly there are two types of QA systems: closed domain question answering systems and open domain question answering system . Also questions can be of different forms: factoid, list, definition, description . Here we focus on factoid type question answering. In Malayalam no efficient question answering systems exist now. Other than keyword processing we need natural language processing techniques for the QA system in Malayalam. Hence this work is important in Malayalam NLP related works. Importance of Karaka Thoery and Vibhakthis for Indian Language ...