Artificial Intelligence in practice – my own system to detect and recognize stuff (goods) in real time. Notice that system recognises very good also parts of used things for tests e.g. part of people body etc. Very good for detecting deficiencies(a damage of goods) on the production line in factories. Solution bases on Deep Machine […]
Read MoreDeep Learning in practice – detection and recognising stuff (goods) in real time
Artificial Intelligence in practice – I wrote a program which on the basis of camera image analysis in real time recognises for instance – playing cats 🙂 It can be used with ease for other solutions – eg detecting intrusions, object monitoring etc. System without any problem recognises animals, things, people etc. Note that […]
Read MoreDeep Learning in practice – recognition bases on camera image analysis in real time
Convolutional neural networks are indeed fascinating. Over a short period of time, they become a disruptive technology, breaking all the state-of-the-art results in multiple domains, from text, to video, to speech going well beyond the initial image processing domain where they were originally conceived[1] https://cs231n.github.io/convolutional-networks/ [1] – text comes from book “Deep Learning with Keras […]
I’d like to recommend one of the best books I’ve ever read about machine learning and keras!!! It perfectly introduces to machine learning issues in technical, practical and mathematical terms Book Description This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional […]
Read MoreDeep Learning with Keras – Antonio Gulli, Sujit Pal
Checkpointing is a process that saves a snapshot of the application’s state at regular intervals, so the application can be restarted from the last saved state in case of failure. This is useful during training of deep learning models, which can often be a time-consuming task. The state of a deep learning model at any […]
Read MoreCheckpointing in Neural Network Models – fault tolerance technique for long running processes
In face recognition problem I’ve used preprocessed data set of the “Labeled Faces in the Wild” (http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz). Our aim is expected results for the top 5 most represented people in the dataset and the algorithm should achieve convergence (values in support column should be the same or close to expected value) Total dataset size: Number […]
Read More[Artificial Intelligence in practice] Faces recognition: SVM classification model – part 1
