One of the simplest models of machine learning is linear regression, but linear models are building blocks of deep neural networks and they are really important. There are two main classes of supervised learning problems, Regression and Classification. In regression, the value of the target is a real value, for example, we try to predict the salary of the given job description.
In classification, the value of the target is a finite set of classes for example if we’re given movie’s review and we try to predict the rating of a movie on a scale of one to five. …
Any deep learning model learns from the data and that data must be collected or uploading on the server (one machine or in a data center). A most realistic and meaningful deep learning model can learn from personal data. Personal data is extremely private and sensitive and no one would like to send or upload it on the server. Federated learning is a collaborative machine learning approach in which we trained a model without centralizing data on the server and this is the main kind of a revolution.
What if we bring the model to the data where it generated instead of bringing data to one location and training a model. …
In my previous article, I explain RNNs’ Architecture. RNNs are not perfect and they mainly suffer from two major issues exploding gradients and vanishing gradients. Exploding gradients are easier to spot, but vanishing gradients is much harder to solve. We use the Long Short Term Memory(LSTM) and Gated Recurrent Unit(GRU) which are very effective solutions for addressing the vanishing gradient problem and they allow the neural network to capture much longer range dependencies.
When backpropagation through time(BPTT ) algorithm gives huge importance to the weights and the values of weights become very large. This could result in values overflow and NaN values for the weights. …
In my previous post, I explain different ways of representing text as a vector. you can read about Word2Vec, Doc2Vec and you can also find a jupyter notebook for Word2Vec model using fastText. We can perform sentiment classification on top of those representations using a dense layer. you can find a jupyter notebook for the sentiment classification using a dense layer on GitHub.
There is one issue with this approach, the dense layer doesn’t consider the order of the words. For example, consider these two sentences
Doc2Vec is an extension of Word2vec that encodes entire documents as opposed to individual words. You can read about Word2Vec in my previous post. Doc2Vec vectors represent the theme or overall meaning of a document. In this case, a document is a sentence, a paragraph, an article, or an essay, etc.
In Doc2Vec, the name of the document, like file name or file ID will be the input, and the sliding window of the words from the document is the output.
Similar to Word2vec, there are two primary training methods, Distributed Memory Model Of Paragraph Vectors (PV-DM) and Paragraph Vector With A Distributed Bag Of Words (PVDBOW). …
In this article, I will try to explain Word2Vec vector representation, an unsupervised model that learns word embedding from raw text and I will also try to provide a comparison between the classical approach One-hot encoding and Word2Vec.
The classical approach of solving text-related problems is one-hot encode the word. This approach has multiple drawbacks.
A Discovery GAN (DiscoGAN) is a generative adversarial network that generates images of products in domain B given an image of domain A. It transfers stylistic elements from one image to another, thus transferring texture and decoration from a fashion item such as a bag to another fashion item such as a pair of shoes. This GAN has numerous applications in the gaming and fashion industry and is worth exploring further for the interested reader.
Pix2Pix network is basically a Conditional GANs (cGAN) that learn the mapping from an input image to output an image. You can read about Conditional GANs in my previous post here and its application here and here. In this post, I will try to explain about Pix2Pix network.
Image-To-Image Translation is a process for translating one representation of an image into another representation.
Generator network uses a U-Net-based architecture. U-Net’s architecture is similar to an Auto-Encoder network except for one difference. Both U-Net and Auto-Encoder network has two networks The Encoder and the Decoder.
Conditional GANs (CGANs) are extensions of the GANs model. You can read about Conditional GANs in my previous post here. In this post, I will try to explain how we can implement a CGANs to perform automatic face aging. Face Aging cGAN(Age-cGANs) introduced by Grigory Antipov, Moez Baccouche, and Jean-Luc Dugelay, in their paper with titled Face Aging With Conditional Generative Adversarial Networks.
The Face Aging-cGan has four networks.
An Encoder : It learns the inverse mapping of input face images and the age condition with the latent vector Z.
Cycle-Consistent Adversarial Networks CycleGANs were proposed by Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. CycleGANs are a novel approach for translating an image from a source domain A to a target domain B. One of the cool feature of CycleGANs is that it doesn’t require paired training data to produce stunning style transfer results.
In many style transfer applications, paired data is a required for the training.
CycleGAN is doesn’t require paired data input to train a models.
A CycleGAN tries to learn a Generator network, which, learns two mappings. CycleGANs train two Generators and two Discriminators networks. …