AI News by La Forge
Contact us

226 articles

#000 Linear Algebra for Machine Learning

2020-03-21 564

Highlights: Linear algebra is a branch of mathematics related to linear equations, linear functions and their representations through matrices and vector spaces. Basically, it is the science of numbers which empowers diverse Data Science algorithms and applications. To fully comprehend machine learning, linear algebra fundamentals are the essential prerequisite. In this post, you will discover what exactly linear algebra is and what are the main applications in the machine learning. Tutorial Ove[...]
Spell - A Streamlined Machine Learning Platform

2020-02-21 230

Meet Spell – data science and machine learning startup that raised 15M$ to bring AI and deep learning to the global workforce. Revenue: unknown Location: New York Founded: 2017. Specialties: Artificial Intelligence, Computer, Machine Learning, Software Spell is an end-to-end data science and machine learning platform that provides the infrastructure for companies and developers to prepare, train, deploy, and manage the full life-cycle of Machine Learning and Deep Learning experiments. Moreover[...]
TF TensorBoard: Visualizing Learning

2019-11-12 206

Highlights: In this post we will learn what is TensorBoard and how to use it. For most people, neural networks can sometimes be a bit of black box. Debugging problems is also a lot easier when we can see what the problem is. Thankfully, TensorBoard is a tool that will help us to analyze neural networks and to visualize learning. Tutorial Overview: Sequential API Model Subclassing Intro The idea of TensorBoard is to help to… Read more
#OD1 YOLO Object Detection

2020-07-16 195

Learn how to use pre-trained weights from yolo v3 in predicting the bounding boxes and class probabilities using keras...
#012 B Building a Deep Neural Network from scratch in Python

2019-11-19 172

To gain a better understanding of how a deep neural network is been built from scratch in python, we will guild you ... don't miss the training process ...
Top 10 Machine Learning Videos on Youtube

2020-02-26 171

Must Watch... 10 top machine learning tutorials on youtube... Get the best experience from some of the best online teachers and educators in the field of machine learning... Learn what it is about and how to apply it in real-world
#024 CNN Convolutional Operation of Sliding Windows

2019-10-29 169 MachineLearning DeepLearning

Learn about sliding windows been applied in convolutional neural networks... how to convert convolutional layers into fully connected layers
How drones can help your crops grow?

2020-01-27 166

Agremo is one of the fastest growing startup in Europe that develops intuitive agricultural sensing and drone analysis platform for drone operators, growers, and agronomists. Location: Belgrade, Serbia Launch date: March 2018 Total funding received: €680K Funding Source South Central Ventures, StartLabs, FRACTALS For several years now, AgroTech startups from all around the world, have been making major and significant changes in the agricultural sector. Their goal is to help make this indu[...]
#012 TF Transfer Learning in TensorFlow

2020-02-17 160

Highlights: In this post we are going to show how to build a computer vision model without building it from scratch. The idea behind transfer learning is that a neural network that has been trained on a large dataset can apply its knowledge to a dataset it has never seen before. That is why it’s called transfer learning; we transfer the learning of an existing model to a new dataset. Tutorial Overview: Introduction Transfer learning with… Read more
#010 C Random initialization of parameters in a Neural Network

2019-10-18 159

After building a neural network another confusing task is tuning your network ... We will learn the effect of random initialization of weights to achieve ....
#011 Deep L-layer Neural Network

2019-10-22 145 DeepLearning ArtificialIntelligence

Before learning to develop your first deep neural network read what it is about ... Here we provide a gentle introduction into a deep neural network ...
#007 Neural Networks Representation

2019-10-31 137

In this post we see the representation of a shallow neural network with one hidden layer and how to implement it from scratch in python.
#003B Gradient Descent

2019-10-11 121

Gradient Descent is an algorithm that tries to minimize the error (cost) function $latex J(w,b)$ and to find optimal values for $latex w$ and $latex b$.
#004 CNN Padding

2019-10-17 118

In order to build deep neural networks, one modification to the basic convolutional operation that we have to use is padding. Let's see how it works.
#004 TF 2.0 TensorFlow Wrappers

2020-02-01 116

Highlights: In this post we are going to talk more about TensorFlow Wrappers. We are going to compare things before and after TensorFlow 2.0. This post will be the introductory one to the series of posts where we are going to build a wide variety of neural networks. To use TensorFlow in our projects, we need to learn how to program using the TensorFlow API. TensorFlow has multiple APIs that can be used to interact with… Read more
#027 CNN Non-Max Suppression algorithm

2019-10-12 115

When using the object detection algorithm, we get many detections. With the support of the non-max suppression algorithm, it detects each object only once.
#001 TF 2.0 An Introduction to TensorFlow 2.0

2020-02-01 113

What is TensorFlow 2.0? TensorFlow is an open source library for numerical computations built by Google Brain team. TensorFlow is based on the data flow graphs. Moreover, it actually allows developers to create data flow graphs—structures that describe how data moves through a graph, or a series of processing nodes. Each node in the graph represents a mathematical operation, and each connection or edge between nodes is a multidimensional data array or a tensor. If… Read more
AI helps blind and low vision people

2020-01-26 113

With use of Artificial Intelligence and Augmented Reality, US company Aira makes lifes of blind people easier. Aira is a service that makes the world instantly more accessible for visually impaired people. They are passionate about transforming daily life of people who are blind or low vision so they can fully Engage, Explore and Experience their world. Through an app on your smartphone, or through an optional pair of Horizon Smart Glasses, Aira delivers instant… Read more
#003 TF 2.0 Eager Execution- A Pythonic way of using TensorFlow

2020-02-01 112 TensorFlow

TensorFlow uses Eager execution, which is a more convenient way to execute the code, and also more “Pythonic”. It is a default choice in the latest version TensorFlow 2.0. In TensorFlow 1.x, we first need to write a Python program that constructs a graph for our computation, the program then invokes, which hands the graph off for execution to the C++ runtime. This type of programming is called declarative programming (specification of the computation… Read more