keras Archives - Petamind

Advanced Keras – Custom loss functions

Tung Nguyen — Wed, 23 Mar 2022 00:31:00 +0000

When working on machine learning problems, sometimes you want to construct your own custom loss function(s). This article will introduce abstract Keras backend for that purpose. Keras loss functions From Keras loss documentation, there are several built-in loss functions, e.g. mean_absolute_percentage_error, cosine_proximity, kullback_leibler_divergence etc. When compiling a Keras model, we often pass two parameters, i.e. […]

The post Advanced Keras – Custom loss functions appeared first on Petamind.

Continue training big models on less powerful devices

Tung Nguyen — Sun, 22 Mar 2020 00:51:57 +0000

It would not be a surprise that you may not have a powerful expensive machine to train a complicate model. You may experience the problem of not enough memory during training in some epoch. This article demonstrates a simple workaround for this. The problem Training deep learning models requires a lot of computing power. For […]

The post Continue training big models on less powerful devices appeared first on Petamind.

MLP for implicit binary collaborative filtering

Tung Nguyen — Mon, 02 Mar 2020 12:11:05 +0000

In this post, we demonstrate Keras implementation of the implicit collaborative filtering. We also introduce some techniques to improve the performance of the current model, including weight initialization, dynamic learning rate, early stopping callback etc. The implicit data For demonstration purposes, we use the dataset generated from negative samples using the technique mentioned in this […]

The post MLP for implicit binary collaborative filtering appeared first on Petamind.

Generate data on the fly – Keras data generator

Tung Nguyen — Fri, 31 Jan 2020 23:13:05 +0000

Previously, we train our model using the pre-generated dataset, for example, in the recommender system or recurrent neural network. In this article, we will demonstrate using a generator to produce data on the fly for training a model. Keras Data Generator with Sequence There are a couple of ways to create a data generator. However, […]

The post Generate data on the fly – Keras data generator appeared first on Petamind.

build a simple recommender system with matrix factorization

Tung Nguyen — Mon, 23 Dec 2019 23:13:25 +0000

We will build a recommender system which recommends top n items for a user using the matrix factorization technique- one of the three most popular used recommender systems. matrix factorization Suppose we have a rating matrix of m users and n items. The rating of user to item is . Similar to PCA, matrix factorization […]

The post build a simple recommender system with matrix factorization appeared first on Petamind.

deep learning: Linear Autoencoder with Keras

Tung Nguyen — Mon, 09 Dec 2019 02:22:01 +0000

This post introduces using linear autoencoder for dimensionality reduction using TensorFlow and Keras. What is a linear autoencoder An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. Autoencoders consists […]

The post deep learning: Linear Autoencoder with Keras appeared first on Petamind.

Recurrent neural network – time-series data- part 1

Tung Nguyen — Fri, 22 Nov 2019 00:09:00 +0000

If you are human and curious about your future, then the recurrent neural network (RNN) is definitely a tool to consider. Part 1 will demonstrate some simple RNNs using TensorFlow 2.0 and Keras functional API. What is RNN An RNN is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence (time […]

The post Recurrent neural network – time-series data- part 1 appeared first on Petamind.

Word2vec with TensorFlow 2.0 – a simple CBOW implementation

Tung Nguyen — Sat, 19 Oct 2019 23:30:20 +0000

In TensorFlow website, there is a good example of word embedding implementation with Keras. Nevertheless, we are curious to see how it looks like when implementing word2vec with PURE TensorFlow 2.0. What is CBOW In the previous article, we introduced Word2vec (w2v) with Gensim library. Word2vec consists of two-layer neural networks that are trained to reconstruct linguistic […]

The post Word2vec with TensorFlow 2.0 – a simple CBOW implementation appeared first on Petamind.

Save, restore, visualise Graph with TensorFlow v2.0 & KERAS

Tung Nguyen — Tue, 08 Oct 2019 12:36:30 +0000

TensorFlow 2.0 is coming really soon. Therefore, we quickly show some useful features, i.e., save and load a pre-trained model, with v.2 syntax. To make it more intuitive, we will also visualise the graph of the neural network model. Benefits of saving a model Quick answer: to save time, easy-share, and fast deploy. A SavedModel […]

The post Save, restore, visualise Graph with TensorFlow v2.0 & KERAS appeared first on Petamind.

A.I in agriculture – Fruit Grading with Keras (part 2)

Tung Nguyen — Sun, 06 Oct 2019 07:05:15 +0000

In part 1, we introduced fruit classification with pure python implementation. In this part, we will use the Keras library instead. What is Keras Keras is an open-sourceneural-network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, Theano, or PlaidML. Designed to enable fast experimentation with deep neural networks, it focuses on being user-friendly, modular, and extensible. […]

The post A.I in agriculture – Fruit Grading with Keras (part 2) appeared first on Petamind.