[artificial intelligence project] Fashion Mnist recognition experiment

[artificial intelligence project] Fashion Mnist recognition experiment This paper mainly carries out the recognition experiment of fashion mnist through four methods, mainly including word bag model, hog feature, mlp multilayer perceptron and cnn convolution neural network. Then don't say much, get up!!! Fashion Mnist Fashion MNIST is an im ...

Posted by peter.t on Tue, 02 Nov 2021 04:03:47 -0700

Python deep learning 4.4 common methods to prevent over fitting (code)

Common methods to prevent over fitting of neural networks include: 1. Reduce network capacity; 2. Add weight regularization; 3. Add dropout; 4. Get more training data. Overfitting and underfitting Over fitting and under fitting In order to prevent the model from learning wrong or irrelevant patterns from the training data, the best solution ...

Posted by updwebmaster on Mon, 01 Nov 2021 03:37:40 -0700

Artificial intelligence Java SDK: cross modal similarity comparison and retrieval of image and text [Chinese]

Image text cross modal similarity comparison and retrieval SDK [Chinese] Note: Due to network reasons, the multilingual version of the CLIP model cannot be downloaded after multiple attempts. https://github.com/FreddeFrallan/Multilingual-CLIP Therefore, the second step is to use the SDK previously made to translate Chinese into English, first ...

Posted by jmrouleau on Sun, 31 Oct 2021 17:41:05 -0700

Artificial intelligence learning

1, What is a decision tree Decision tree is a method of machine learning. The generation algorithms of decision tree include ID3, C4.5 and C5.0. Decision tree is a tree structure, in which each internal node represents a judgment on an attribute, each branch represents the output of a judgment result, and finally each leaf node represents ...

Posted by Boris Senker on Sat, 30 Oct 2021 22:33:25 -0700

[basis of artificial intelligence] realizing fuzzy reasoning system of washing machine in python

Operating environment Pycharm + Anaconda3 A set of fuzzy sets of sludge and oil parameters and the corresponding washing time reasoning results are known. Now a group of fuzzy sets of sludge and grease are given, fuzzy reasoning is carried out, and the fuzzy set of washing time is deduced. Finally, the fuzzy decision is made to select the ...

Posted by seidel on Sat, 30 Oct 2021 11:13:23 -0700

Face feature extraction (Dlib + opencv3.4 + Python 3.8)

1, dlib library introduction and related installation 1.1 INTRODUCTION Dlib library is an open source library of machine learning, which contains many algorithms of machine learning. It is very convenient to use. It can directly include header files, and does not depend on other libraries (with its own image codec library source code). Dl ...

Posted by Mick33520 on Sat, 30 Oct 2021 04:19:59 -0700

Artificial intelligence -- genetic algorithm to solve TSP problem (JAVA version)

TSP problem, also known as traveling salesman problem and salesman problem.         Problem Description: in the given city map, the traveler is required to travel through all cities, and each city can only be visited once, so as to find the shortest path for the traveler to travel through all cities.       ...

Posted by wildmalc on Fri, 29 Oct 2021 19:21:03 -0700

Principle and code analysis of the strongest ViT (Vision Transformer) in the whole network

    Today, let's learn more about Vision Transformer. timm based code. 1. Patch Embedding Transformer was originally used to do NLP work, so ViT's primary task is to convert the graph into word structure. The method adopted here is to divide the picture into small blocks, as shown in the lower left corner of the above figure. Eac ...

Posted by warran on Fri, 29 Oct 2021 10:38:15 -0700

DB4AI: enable database native AI computing, and data relocation from complex to simple

DB4AI tries to help users get rid of tedious data handling, export and management by implanting AI computing power into the database. It sounds reasonable to use the database to store massive data, but in the face of a traditional database, users as algorithm engineers or AI beginners have to export the data of the data set and then import it i ...

Posted by crabfinger on Thu, 28 Oct 2021 19:21:52 -0700

Artificial intelligence series: search for pictures with pictures

Introduction to image search platform The image search platform supports two types of image search: General image search: 512 dimensional features are extracted using the pre trained model on the ImageNet dataset: resnet50Portrait high-precision search: before face feature extraction (512 dimensional feature extraction using face feature mode ...

Posted by svanderclock on Thu, 28 Oct 2021 05:34:36 -0700