GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → ankonzoid → NN-scratch

ankonzoid / NN-scratch

Licence: MIT license
Coding up a Neural Network Classifier from Scratch

Programming Languages

python
139335 projects - #7 most used programming language

Labels

classifierdata-sciencemachine-learningtutorialaideep-learningneural-networkartificial-intelligencedatasetneural-networksclassification

Projects that are alternatives of or similar to NN-scratch

text2class
Multi-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT
Stars: ✭ 15 (-80.77%)
Mutual labels:  classifier, classification
dl-relu
Deep Learning using Rectified Linear Units (ReLU)
Stars: ✭ 20 (-74.36%)
Mutual labels:  classifier, classification
classy
Super simple text classifier using Naive Bayes. Plug-and-play, no dependencies
Stars: ✭ 12 (-84.62%)
Mutual labels:  classifier, classification
Sytora
A sophisticated smart symptom search engine
Stars: ✭ 111 (+42.31%)
Mutual labels:  classifier, classification
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: ✭ 38 (-51.28%)
Mutual labels:  classifier, classification
support-tickets-classification
This case study shows how to create a model for text analysis and classification and deploy it as a web service in Azure cloud in order to automatically classify support tickets. This project is a proof of concept made by Microsoft (Commercial Software Engineering team) in collaboration with Endava http://endava.com/en
Stars: ✭ 142 (+82.05%)
Mutual labels:  classifier, classification
ML4K-AI-Extension
Use machine learning in AppInventor, with easy training using text, images, or numbers through the Machine Learning for Kids website.
Stars: ✭ 18 (-76.92%)
Mutual labels:  classifier, classification
Awesome Fraud Detection Papers
A curated list of data mining papers about fraud detection.
Stars: ✭ 843 (+980.77%)
Mutual labels:  classifier, classification
Multi Matcher
simple rules engine
Stars: ✭ 84 (+7.69%)
Mutual labels:  classifier, classification
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (+53.85%)
Mutual labels:  classifier, classification
R-Machine-Learning
D-Lab's 6 hour introduction to machine learning in R. Learn the fundamentals of machine learning, regression, and classification, using tidymodels in R.
Stars: ✭ 27 (-65.38%)
Mutual labels:  classification
MoeFlow
Repository for anime characters recognition website, powered by TensorFlow
Stars: ✭ 113 (+44.87%)
Mutual labels:  classification
Metric Learning Adversarial Robustness
Code for NeurIPS 2019 Paper
Stars: ✭ 44 (-43.59%)
Mutual labels:  classification
newt
Natural World Tasks
Stars: ✭ 24 (-69.23%)
Mutual labels:  classification
ml-competition-template-titanic
Kaggle Titanic example
Stars: ✭ 51 (-34.62%)
Mutual labels:  classification
HateALERT-EVALITA
Code for replicating results of team 'hateminers' at EVALITA-2018 for AMI task
Stars: ✭ 13 (-83.33%)
Mutual labels:  classification
Conformer
Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition
Stars: ✭ 345 (+342.31%)
Mutual labels:  classification
embeddings
Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language
Stars: ✭ 27 (-65.38%)
Mutual labels:  classification
Machine-Learning-Specialization
Project work and Assignments for Machine learning specialization course on Coursera by University of washington
Stars: ✭ 27 (-65.38%)
Mutual labels:  classification
tensorflow-image-classifier
Easily train an image classifier and then use it to label/tag other images
Stars: ✭ 29 (-62.82%)
Mutual labels:  classifier
View All Similar Projects ➔

Coding up a Neural Network classifier from scratch

We train a multi-layer fully-connected neural network from scratch to classify the seeds dataset (https://archive.ics.uci.edu/ml/datasets/seeds). An L2 loss function, sigmoid activation, and no bias terms are assumed. The weight optimization is gradient descent via the delta rule.

Usage

Run:

python3 NN_scratch.py

The output should look like:

Reading 'data/seeds_dataset.csv'...
 -> X.shape = (210, 7), y.shape = (210,), n_classes = 3

Neural network model:
 input_dim = 7
 hidden_layers = [5]
 output_dim = 3
 eta = 0.1
 n_epochs = 400
 n_folds = 4
 seed_crossval = 1
 seed_weights = 1

Cross-validating with 4 folds...
 Fold 1/4: acc_train = 98.10%, acc_valid = 94.23% (n_train = 158, n_valid = 52)
 Fold 2/4: acc_train = 98.10%, acc_valid = 98.08% (n_train = 158, n_valid = 52)
 Fold 3/4: acc_train = 98.73%, acc_valid = 96.15% (n_train = 158, n_valid = 52)
 Fold 4/4: acc_train = 98.73%, acc_valid = 94.23% (n_train = 158, n_valid = 52)
  -> acc_train_avg = 98.42%, acc_valid_avg = 95.67%

Libraries required:

  • numpy, pandas
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].