Ai Pool
17  septembre     17h48
DenseNet
   Densely Connected Convolutional Networks (CVPR 2017 Best Paper Award) Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to t...
29  mai     13h40
Introduction of Fast Fourier Transformation (FFT)
   This article comprises of introduction to the Fourier series, Fourier analysis, Fourier transformation, why do we use it, an explanation of the FFT algorithm, and its implementation.
10  mai     18h00
Linear and Logistic Regression
   Intuition and implementation behind the base algorithms for supervised machine learning
29  juillet     18h20
AlexNet
   ImageNet Classification with Deep Convolutional Neural Networks We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data...
13  mai     16h07
Optimization Methods, Gradient Descent
   This article covers a sublime explanation and a simple example of Vanilla Gradient Descent algorithm, Stochastic Gradient Descent, Momentum Optimizer, and Adam Optimizer in which RMSProp is also explained
14  mai     16h19
Confidence Interval Understanding
   Explanation of confidence intervals and the how-to calculate it for different scenarios, and also the equation that makes the confidence interval and the parameters involved with it
10  mai     18h02
Yolov3 and Yolov4 in Object Detection
   Explanation of object detection with various use cases and algorithms. Specifically, how the yolov3 and yolov4 architectures are structured, and how they perform object detection
    17h57
Activation Functions for Neural Networks
   In this article, explaination of various activation functions has been given like Linear, ELU, ReLU, Sigmoid, and tanh.
01  décembre     14h20
Mask R-CNN
   We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called ...
12  février     17h04
PoolNet
   One of the top state-of-the-art results for the salient object detection has the PoolNet model, which performs well with different backbone models, such as VGG or ResNet . The key operation of this model is pooling operation, which let’...
15  mai     12h19
Using Autoencoder to generate digits with Keras
   This article contains a real-time implementation of an autoencoder which we will train and evaluate using very known public benchmark dataset called MNIST data.
08  juin     18h19
Visualization with Seaborn
   This article will enable you to use the seaborn python package to visualize your structured data with seaborn barchart, scatter plot, seaborn histogram, line, and seaborn distplot.
19  août     13h09
Cuda Version
   How to know the version of Cuda installed on your pc? I’m using Keras with TensorFlow back-end, but I need to detect the version of Cuda in my code. It does not matter the solution is with Keras or TensorFlow ....
    13h11
Tensorflow Lite Speed Report
   I’ve got a model in TensorFlow lite , it’s not as fast as I wanted to be. I would like to know what the problem is, which layer makes it to be so slow. Is there a way, that I can test the speed for each layer ?...
30  août     16h53
Pix2Pix
   Image-to-Image Translation with Conditional Adversarial Networks We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output ...
04  septembre     17h04
SegNet
   Abstract-We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network...
10  mai     18h03
Normalization in Deep learning
   Different types of Normalization in Deep Learning. A very useful technique to avoid overfitting and generalize your model better.
11  mai     17h24
Understanding of Regularization in Neural Networks
   This article includes the different techniques of regularization like Data Augmentation, L1, L2, Dropout, and Early Stopping
10  mai     17h59
Random Forests Understanding
   Intuition and Implementation on a key algorithm to reduce overfitting in tree based algorithms
19  août     13h10
Why network overfits too early?
   I want to train a neural network model, which basically does binary classification. I can’t understand why my network overfits too early. I thought my network is too big and it memorizes the dataset, but when I make it smaller, it does not learn at all. How avoid this situation? Dropout didn’t...
24  mai     16h10
Understanding of Probability Distribution and Normal Distribution
   Introduction of probability distribution and its types. Here you can find the intuition about the normal or gaussian distribution, standard normal distribution with the normal curve and normal distribution formula.
02  octobre     16h21
HarDNet
   State-of-the-art neural network architectures such as ResNet, MobileNet, and DenseNet have achieved outstanding accuracy over low MACs and small model size counterparts. However, these metrics might not be accurate for predicting the inference time. We sug...
19  août     13h11
What to do when you have small dataset
   I’m trying to train a classifier with a neural network, but I’ve got too small datasets. Each class has about 1k examples. What is the best approach?...
15  mai     10h22
Understanding of Support Vector Machine (SVM)
   Explanation of the support vector machine algorithm, the types, how it works, and its implementation using the python programming language with the sklearn machine learning package
14  mai     16h15
Decision Trees
   Intuition and implementation of the first tree-based algorithm in machine learning
10  mai     18h02
End-To-End PyTorch Example of Image Classification with Convolutional Neural Networks
   Image classification solutions in PyTorch with popular models like ResNet and its variations. End-To-End solution for CIFAR10 100 and ImageNet datasets.
30  juillet     15h37
Pix2Pix
   Image-to-Image Translation with Conditional Adversarial Networks We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output ...
05  septembre     17h59
DCGAN
   Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised ...
19  août     13h10
Multiple cuda versions installed in machine
   I’m using TensorFlow and I have some old projects which are written with TensorFlow 1.4 and older. Some of them don’t work with a new version of Cuda . Can I have multiple Cuda with different versions at the same time?...
10  mai     18h00
Supervised learning with Scikit-Learn Library
   How to create a model for supervised learning like linear and logistic regression with scikit-learn python library
    18h04
Diving into Object Detection Basics
   A guide for Object Detection basic concepts which cover What is Object Detection and how does it work, Concept of Anchor Boxes, Why is Loss function necessary, some free datasets, and finally, implementation of SSD.
    18h03
Dropout in Deep Learning
   Understanding Dropouts in Deep Learning to reduce overfitting
14  mai     16h01
Dimensionality Reduction, PCA Intro
   We will be covering a dimensionality reduction algorithm called PCA (Principal Components Analysis) and will show how it helps to understand the data you have.
13  mai     18h17
Understanding Autoencoders - An Unsupervised Learning approach
   This article covers the concept of Autoencoders. Concepts like What are Autoencoders, Architecture of an Autoencoder, and intuition behind the training of Autoencoders.
30  juillet     17h23
DCGAN
   Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised lea...