Tech Port 21

   GANs consist of three terms Generative Adversarial Network. Let's understand these three terms first. Generative : A Generative Model takes input training sample from some distribution and learns to represents that distribution. Adversarial : It basically means Conflicting or Opposing. Networks : These are basically neural networks. So,Generative Adversarial Networks are deep neural network architecture comprising of two neural networks compete with each other to make a generative model. A GAN consist of two class models : Discriminative Model :- It is the one that discriminate between two different classes of data.It tries to identify real data from fakes created by the generator Generative Model :- The Generator turns noise into an imitation of the data to try to trick the discriminator Mathematically, A Generative Model 'G' to be trained on training data 'X' sampled from some true distribution 'D' is the one which, given some standard random distrib

 Machine Learning It is basically a Subset of AI (Artificial Intelligence) which enables Machine to Learn from Data.     Hmm... So, What is AI and what does a Subset of AI means? Artificial Intelligence is basically the domain of producing Intelligent Machines. All the machine which performs some smart activity can be called as an Artificially Intelligent Machine like an Air Conditioner changing the Temperature inside the room by sensing the Temperature from the outside. Such machines are not using any Machine Learning or Deep Learning Techniques.So such machine might come in the Artificial Intelligent set but not in the Machine Learning or Deep Learning part.   How does a Machine Learns from Data? A Machine Learns from data using a Machine Learning Algorithm which take's the data as an input and predicts the output by finding patterns in the data.   Machine Learning Algorithms can be broadly divided into 3 types : Supervised Learning Unsupervised Learning Reinforcement Learning S

 Image An Image consists of a set of pixels, which are the buildings blocks for any image. Every Pixels defines the color or the intensity of light.      Suppose an image has a resolution of 1000 x 750,which mean that it is 1000 pixels wide and 750 pixels tall. So the total number of pixels in our image will be 1000 * 750 = 7,50,000 pixels. An Image can be of two type :- Grayscale Color A Grayscale image can have a pixel value between 0 and 255, here 0 means the pixel is 'Black' and 255 means the pixel is ' White'. All the values in between represents various shades of gray. The matrix obtained from a Grayscale Image is 2-Dimensional ie it has width and height. A Color image is represented in RGB color space.The matrix obtained from a color image is a 3D matrix with parameter of Width, Height and Depth. Pixels in the RGB color space are no longer a scalar value like in a grayscale/single channel image – instead, the pixels are represented by a list of three values:

 What is Linear Regression? This Algorithm is used to find the relationship between 2 continuous variables [ one independent variable and one dependent variable ]. It is a linear model which assumes a linear relationship between input and output variables. If we have single input variables then we call it as simple linear regression, if we have multiple we call it as multiple linear regression. It is both a statistical algorithm and machine language algorithm.  The Equation is 'Y = M * X + C' Y = Independent Value M = Slope/Weight X = Dependent Value C = Bias The Core idea is to obtain a line that best fits the data. 'Y' is the output variable we want to predict, X is the input variable and M & C can be called as coefficients that we need to estimate. To find m and b values we have methods like statistical method or ordinary least squares or gradient descent. How does it Work? Goal is to find the best fit line which minimize the error ( distance between the line and

  Machine Learning sub-set of Artificial Intelligence focuses mostly on Machine. In this, computer algorithms are reinforced by training automatically, resulting in increased efficiency and better prediction. It detects similarities in the data, allowing data-driven decisions to be taken by the computer or system rather than being directly designed to do a certain task. Machine Learning Terms You Should Know Data Wrangling Data Wrangling also know as Data Cleaning or "munging", is the process of gathering, selecting, cleaning , structuring and enriching raw data into the desired format for better decision making in less time. Data wrangling help to create an efficient ETL (Extract Transform and Load) or create beautiful data visualizations.It can take a lot of work and time but it is worth the time and effort as it can give vital information from the data. Data Imputation  Data Imputation is the substitution of estimated values for missing or inconsistent data item (fields).

Computer vision is an interdisciplinary scientific field which deals with how digital images or videos can obtain high-level understanding from computers. It attempts to understand and automate activities that the human visual system can do from the point of view of engineering.Computer vision is also used in convenience stores, Driverless car training, everyday medical diagnostics, and in tracking the health of crops and animals, as an AI system that helps machines to interpret and mark images. We have seen from our study that machines are talented in identifying pictures. 5 Must Know Computer Vision Tools are: YOLO YOLO (You Only Look Once) is an open source object detection approach, which has a number of benefits compared to the other approaches. YOLO nicely learns the context and can learn 'generalized' representation so well that could be used on images with different objects. YOLO is extremely fast. Paper :- https://arxiv.org/pdf/1506.02640v5.pdf Scikit-Image  It is an o

A Python library is a reusable piece of code that you may want to use in your programs/projects. Compared to languages such as C++ or C, Python libraries do not have a clear background in Python.Today, more than 137,000 Python libraries are present. Python libraries play a crucial role in creating applications for machine learning, data science, visualization techniques, image and data manipulation, and more.   1. Pandas Pandas is a software library written for the Python programming language for data manipulation and analysis. Pandas is a fast, powerful, flexible and easy to use open source data analysis and manipulation tool, built on top of the Python programming language. In particular, it offers data structures and operations for manipulating numerical tables and time series. Pandas has been one of the most popular and favorite data science tools used in Python programming language for data wrangling and analysis. Data is unavoidably messy in real world. And Pandas

 Machine learning is one of the most exciting techniques one has ever encountered.The field of study that gives computers the ability to learn without being explicitly programmed is machine learning.Their are platforms that can help you improve your Machine Learning skills. Today I've come up with the list of some of my favorite platforms.   Platforms to Improve Machine Learning Skills 1. Kaggle The online community of data scientists and machine learning practitioners is Kaggle, a subsidiary of Google LLC. Kaggle is the largest data science community in the world.Kaggle enables users in a web-based data-science environment to find and publish data sets, explore and build models, work with other data scientists and machine learning engineers, and enter competitions to solve challenges in data science.With it's free GPUs, high paying competitions,massive community , thousands on datasets and notebooks, this platform helps a lot. 2. Seedbank It was launched by  'TensorFlow