Category «Tensorflow»

Word Encoding and Embedding Algorithms

When we start communicating with a machine there is only one issue machine never understand different categories by name. If we tell a machine the colour of a balloon is red it will not understand  ‘Red’ rather than it will keep it as 255,0,0 0r 1,0,0 it means it encodes it in its own mother …

CNN-Convolution Neural Network

When we enter into the world of computer vision we have to understand how a computer understands an image. A colored image has three channels and a 2D data in each channel. When the image size increases Machine learning start suffering from the curse of dimensionality, in order to overcome from this Deep learning comes up …

keras-Tensorboard

Many times we need to visualize our model on Tensorboard, for this we have to save our model and at runtime check out the performance. Here is the code for a simple linear regression using Keras and tensorboard. import Libraries: import keras import numpy as np from pandas import read_csv from keras.models import Sequential from …

Heteroscedasticity (Heteroskedasticity)

Heteroscedasticity refers to the condition in which the variability of a variable is unequal across the range of values of a second variable that predicts it. A scatterplot of these variables will often create a cone-like shape, as the scatter (or variability) of the dependent variable (DV) widens or narrows as the value of the independent …

CNN

CNN stands for convolutional neural network. It is mostly used for developed for object recognition tasks such as handwritten digit recognition. There are four types of layers in a Convolutional Neural Network: 1. Convolutional Layers. 2. Pooling Layers. 3. Fully-Connected Layers. 4.Dropout layers. CNN is just a function which operates on another function in the below …

Gradient Descent

Gradient Descent Gradient Descent is an optimization algorithm that optimize the cost of the function.The goal is to continue to try different values for the coefficients, evaluate their cost and select new coefficients that have a slightly better (lower) cost. https://www.hackerearth.com/blog/machine-learning/3-types-gradient-descent-algorithms-small-large-data-sets/ https://medium.com/@zhaoyi0113/python-implementation-of-batch-gradient-descent-379fa19eb428 Introduction to Gradient Descent Algorithm (along with variants) in Machine Learning