machine learning

BLAS vs BLIS

BLAS (Basic Linear Algebra Subprograms) and BLIS (BLAS Like Interface Software) are libraries that have revolutionized scientific computing by accelerating execution of mathematical operations on a vast range of platforms. In short, BLIS is the new generation alternative to BLAS

machine learning

Types of Neural Network optimizations

The types of neural network optimizations are weight pruning, structured pruning, convolution, fully-connected, structured group, structure ranking with activations like Lp norm, block pruning, model thinning, compression schedule, regularization, group lasso, group variance, quantization and others

machine learning

Principle of Sammon Mapping

Sammon mapping (also known as Sammon projection) is an algorithm that maps a high dimensional data to lower dimensional data by preserving the structure of inter point distances in the original data. Learn why Sammon Mapping is better than Principal Component Analysis (PCA)

machine learning

Build / Install Eigen Library from source

In this article, we explore the way to build and install Eigen library from source using cmake. Eigen is an efficient open-source C++ library for linear algebra, matrix and vector operations, geometrical transformations, numerical solvers and related algorithms.

machine learning

Key ideas that makes Graphics Processing Unit (GPU) work so fast

We have explored the key ideas that are used in Graphics Processing Unit to make it so fast. Ideas include many cores in parallel, pack cores full of ALUs by sharing instruction stream by explicit SIMD vector instruction and avoid latency stalls by interleaving execution of many groups.

machine learning

Basic Graphics Processing Unit (GPU) design concepts

we have explored some of the basic architecture concepts in Graphics Processing Unit (GPU) such as graphics pipeline, vector processing, primitive processing, rasterization, fragment processing, pixel operations, graphics architecture and shader programming model There are five basic graphics entity

machine learning

What is a Graphics Processing Unit (GPU)?

A graphics processing unit (GPU) is a processor like CPU and TPU for faster graphics processing. Specifically, it designed to rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer to be displayed on a screen. GPUs are developed by Intel, Nvidia and AMD (ATI).

machine learning

Tensor Processing Unit (TPU) explained

A tensor processing unit (TPU) is a proprietary processor designed by Google in 2016 for use in neural networks inference. Norm Jouppi was the Technical leader of the TPU project. Key ideas in TPU include Matrix Multiplier Unit, Unified Buffer, Activation Unit and systolic array

machine learning

When to use Multilayer Perceptrons (MLP)?

Multilayer Perceptrons (MLPs) are the buiding blocks of neural network. They are comprised of one or more layers of neurons. MLPs are used for classification prediction problems, regression prediction problems and tabular datasets.

machine learning

When to use Recurrent Neural Networks (RNN)?

Recurrent Neural Networks (RNNs) are designed to work with sequence prediction problems. RNNs can be used on Text data, Speech data, Classification prediction problems, Regression prediction problems and Generative models. Sequence prediction problems come in many forms.

machine learning

When to use Convolutional Neural Networks (CNN)?

Use CNN for data with a spatial relationship. Convolutional Neural Networks (CNNs) are designed to map image data to an output variable. They have proven so effective that they are the ready to use method for any type of prediction problem involving image data as an input

tensorflow

Run TensorFlow Convolutional Neural Network (TF CNN) benchmarks in CPU

We will walk you through running the official benchmark of (TF CNN benchmark) TensorFlow for Convolutional Neural Network on your machine. The process is simple and we have divided it into three simple steps: install tensorflow, get the benchmarking code and run the benchmark and observe results

data science

Basic Data Science concepts everyone needs to know

In this article, we explored some of the basic data science concepts everyone needs to understand to ace things in real life. We demonstrated basic statistic measurements such as median, bayesian statistics, probability distribution, dimensionality reduction and over and under sampling of data.

machine learning

Difference between MKL, MKL ML and MKL DNN

In this article, we give the relation between MKL, MKL ML and MKL DNN. MKL is a closed sourced BLAS library while MKL ML is an open-source BLAS library which is actually a subset of MKL. MKL DNN is an open source library used to optimize Deep Neural Network operations and depends on a BLAS library.

eigen

What is Eigen C++ Library?

Eigen is an efficient open-source C++ library for linear algebra, matrix and vector operations, geometrical transformations, numerical solvers and related algorithms. It has been developed by two great developers namely Benoit Jacob and Gael Guennebaud. It has support for compilers like GCC

openblas

Install OpenBLAS from source

In this article, we will guide you to install OpenBLAS from source in three simple steps. OpenBLAS is an open source optimized BLAS (Basic Linear Algebra Subprograms) library based on GotoBLAS2 1.13 BSD version.

machine learning

Building a Convolution Neural Network (CNN) for handwritten digit recognition in Python using Keras

We built a Convolution Neural Network (CNN) for handwritten digit recognition from scratch in python. We will be using Keras API with TensorFlow backend and use handwritten digits dataset from Kaggle.

machine learning

Why Principal Component Analysis (PCA) works?

We have demonstrated how and why Principal Component Analysis (PCA) works using the intuition behind the common operations used in the algorithm such as Variance, Covariance, Eigenvectors and Eigenvalues. Eigenvectors represent directions while Eigenvalues represent magnitude the importance

machine learning

Algorithm of Principal Component Analysis (PCA)

The algorithm of Principal Component Analysis (PCA) is based on a few mathematical ideas namely Variance, Convariance, Eigen Vectors and Eigen values. The algorithm is of eight simple steps including preparing the data set, calculating the covariance matrix, eigen vectors and values, new feature set

machine learning

Basic Ideas of Principal component analysis

Principal component analysis (PCA) is a technique to bring out strong patterns in a dataset by supressing variations. It is used to clean data sets to make it easy to explore and analyse. We have demonstrated an example of 17 dimensions and given the basic intuition of PCA

machine learning

Top deep learning frameworks to explore

In this article, we have explored some of the top Deep Learning frameworks that are out there and you should definitely try out. Some of them are TensorFlow, Keras, Caffe, Caffe2, MXNet, CNTK, BigDL, Torch, PyTorch, deeplearn.js and others

machine learning

Popular Datasets in Machine Learning

Data sets are important in Machine learning as the more better data we have, the better the model. The various popular data sets available for machine learning are ImageNet, MNIST, NIST, CIFAR-10 and YouTube 8M.

tensorflow

Key ideas in TensorFlow

TensorFlow is a popular Deep Learning library that is used to build Deep Learning models and is backed by Google. A few key ideas of TensorFlow are tensor, distributed computing, kernel abstraction, operation abstraction, computational graph, automatic gradient computation and others

tensorflow

Build and install TensorFlow from source with MKL DNN support and AVX enabled

In this guide, we will walk you through building and installing TensorFlow from source with support for MKL DNN and with AVX enabled. By following the six simple steps, you can build and install TensorFlow from source in 20 minutes

machine learning

Differences between Torch and PyTorch deep learning libraries

We have explored some of the differences between two popular frameworks namely Torch and PyTorch from the view of common origin, current development status, source code and implementation, usage, performance and ONNX support. As development of Torch has been paused, you should go with PyTorch