AI News, TensorFlow - Not Just for Deep Learning
TensorFlow - Not Just for Deep Learning
(Chinese translation here (中文) by Xiatian) One time when I was illustrating the code base and architecture of TensorFlow to my friends, they were quite surprised by how much more code was introduced since TensorFlow’s first open-source release.
They were only expecting several popular types of deep learning algorithms from the code base as heard from other people and social media.
In this blog post, I will introduce the wide range of general machine learning algorithms and their building blocks provided by TensorFlow in tf.contrib.
TF.Learn is a high-level module inside TensorFlow that provides various number of machine learning algorithms inside it’s estimators module.
They are often used to solve optimization problems for numeric analysis, including optimizing parameter space to find a better model.
Regularizers, such as L1 and L2 regularizations, available in tf.contrib.layers.regularizers module, are often used to reduce the risk of overfitting by penalizing the large number of features used in the model.
There are additional functions in tf.contrib.layers.embedding that convert high-dimensional categorical features into a low-dimensional and dense real-valued vector, often referred to as an embedding vector.
TensorFlow provides a wide range of loss functions to choose inside tf.contrib.losses, such as sigmoid and softmax cross entropy, log-loss, hinge loss, sum of squares, sum of pairwise squares, etc.
Learn and Improve your Machine Learning Skills with TensorFlow’s Free Seedbank Platform
Seedbank enables you to learn and discover various new machine learning examples and assists you in understanding and implementing your ideas.
The various learning categories Seedbank is offering include ‘classification’, ‘unsupervised learning’, ‘text and language’, ‘recurrent nets’, etc., comprising machine learning examples, tutorials and algorithms.
Apart from this, TensorFlow Hub provides numerous pretrained machine learning modules along with the Colaboratory notebooks (machine learning codes by Google).
After you select the Colab notebook, you’ll be connected to a free GPU kernel where you can start working through the example or tutorial.
At present, Seedbank is able to track only notebooks by Google though the team is planning to index user-created content in the near future.
- On Wednesday, January 16, 2019
Train an Image Classifier with TensorFlow for Poets - Machine Learning Recipes #6
Monet or Picasso? In this episode, we'll train our own image classifier, using TensorFlow for Poets. Along the way, I'll introduce Deep Learning, and add context ...
1.3: Python Anaconda for Deep Learning, Keras and Tensorflow (Module 1, Part 3)
An introduction to Anaconda Python for deep learning with Keras and TensorFlow. An introduction is provided for vectors, dictionaries, and other Python ...
TensorFlow Tutorial #19 Hyper-Parameter Optimization
How to find good hyper-parameters for a Neural Network in TensorFlow and Keras using Bayesian Optimization and Gaussian Processes from scikit-optimize.
How to Make an Amazing Tensorflow Chatbot Easily
We'll go over how chatbots have evolved over the years and how Deep Learning has made them way better. Then we'll build our own chatbot using the ...
TensorFlow Tutorial #23 Time-Series Prediction
How to predict time-series data using a Recurrent Neural Network (GRU / LSTM) in TensorFlow and Keras. Demonstrated on weather-data.
Tensorflow 17 Regularization dropout (neural network tutorials)
This tutorial code: The problem in real life is complicated, and we always face to ..
Using Jupyter Notebooks to Run Deep Learning Algorithms - 2017 AWS Online Tech Talks
Learning Objectives: - Creating a ssh tunnel between the client device and the instance. - Configurations on EC2 to allow security allow communication. - Create ...
Real-Time Machine Learning with Node.js by Philipp Burckhardt, Carnegie Mellon University
Real-Time Machine Learning with Node.js - Philipp Burckhardt, Carnegie Mellon University Real-time machine learning provides statistical methods to obtain ...
CppCon 2017: Peter Goldsborough “A Tour of Deep Learning With C++”
— Presentation Slides, PDFs, Source Code and other presenter materials are available at: — Deep .