Over the past several years, Convolutional Neural Networks (CNNs) have established themselves as a state-of-the-art computer vision tool both in industry and academia. Being used in applications ranging from facial recognition to self-driving cars, they have become incredibly popular for deep learning developers. In my work at Galaxy.AI, I've implemented CNNs for some of the more "traditional" computer vision tasks such as image classification and object localization. In addition to these sorts of tasks, however, CNNs have been shown to be particularly good at recognizing artistic style. Specifically, in this paper from 2015, the authors discuss how deep convolutional neural networks can distinguish between "content" and "style" in images.

Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms.

Understanding how artificial intelligence works may seem to be highly overwhelming, but it all comes down to two concepts, machine learning, and deep learning. These two terms are usually used interchangeably assuming they both mean the same, but they are not. Both the terms are not new to us, but the way they are utilized to describe intelligent machines has always been changing. It is important for organizations to clearly understand the difference between machine learning and deep learning. By definition, machine learning is a concept in which algorithms parse the data, learn from it, and then apply the same to make informed decisions.

After the celebrated victory of AlexNet [1] at the LSVRC2012 classification contest, deep Residual Network [2] was arguably the most groundbreaking work in the computer vision/deep learning community in the last few years. ResNet makes it possible to train up to hundreds or even thousands of layers and still achieves compelling performance. Taking advantage of its powerful representational ability, the performance of many computer vision applications other than image classification have been boosted, such as object detection and face recognition. Since ResNet blew people's mind in 2015, many in the research community have dived into the secrets of its success, many refinements have been made in the architecture. This article is divided into two parts, in the first part I am going to give a little bit of background knowledge for those who are unfamiliar with ResNet, in the second I will review some of the papers I read recently regarding different variants and interpretations of the ResNet architecture.

Building machines that can learn from examples, experience, or even from another machines at human level are the main goal of solving AI. That goal in other words is to create a machine that pass the Turing test: when a human is interacting with it, for the human it will not possible to conclude if it he is interacting with a human or a machine [Turing, A.M 1950]. The fundamental algorithms of deep learning were developed in the middle of 20th century. Since them the field was developed as a theory branch of stochastic operations research and computer science, but without any breakthrough application. But, in the last 20 years the synergy between big data sets, specially labeled data, and augmentation of computer power using graphics processor units, those algorithms have been developed in more complex techniques, technologies and reasoning logics enable to achieve several goals as reducing word error rates in speech recognition; cutting the error rate in an image recognition competition [Krizhevsky et al 2012] and beating a human champion at Go [Silver et al 2016].

'Capsule Networks' and'Inverse Graphics' seem like intimidating and somewhat vague terms when heard for the first time. These terms weren't prevalent in mainstream media until recently, after the godfather of deep learning, Geoffrey Hinton, came out with two papers on Dynamic Routing between Capsules and on Matrix Capsules with EM Routing [This is currently a blind submission under review for ICLR 2018 but let's be honest, we know it's going to be Hinton et al.]. In this article, I will try to distill these ideas and explain the intuition behind them and how these are bringing machine learning models in computer vision one step closer to emulating human vision. Starting with the intuition behind CNNs, I'll dive into how they arise from our hypotheses about the neuroscience behind human sight and how inverse graphics is the way to create the next generation of computer vision systems and finally give a brief overview of how all of this connects to Capsule Networks. Research about the neuroscience and human sight led us to realize the fact that humans learn and analyze visual information hierarchically.

Keras models follow Scikit-learn's interface of fit/predict with some notable extensions.

Read an article in Quanta Magazine about a talk done a month or so ago given by Professor Naftali (Tali) Tishby on his theory that all deep learning convolutional neural networks (CNN) exhibit an "information bottleneck" during deep learning.

The result of this process is an input image where the filter is very active. Remember that each filter acts as a detector for a particular feature. The input image we generate will contain a lot of these features. We will visualize filters at the last layer of each convolution block. To clear any confusion, in the previous section we visualized the feature maps, the output of the convolution operation. Now we are visualizing the filters, the main structure used in the convolution operation. We will visualize 8 filters per layer.

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models consisting of an encoder model to produce a hidden representation of the source text, followed by a decoder model to generate the target. While such models have significantly fewer pieces than earlier systems, significant tuning is still required to achieve good performance. For text generation models in particular, the decoder can behave in undesired ways, such as by generating truncated or repetitive outputs, outputting bland and generic responses, or in some cases producing ungrammatical gibberish. This paper is intended as a practical guide for resolving such undesired behavior in text generation models, with the aim of helping enable real-world applications.