Deep Learning has given us a new way to think about things. Partially, the reason is that they can be made arbitrarily big, allowing them to have immense capacity, and they can be regularised, preventing overfitting. However, it is not very easy to understand how these models work. In this post, I will show a simple technique that allows somebody to somewhat see what the model is doing. I will go over the individual components, how to use them together, and at the end of the post, I will link to the source code to get started.

What is Intel doing in the area of artificial intelligence/machine learning? Artificial intelligence is causing a technological revolution. Intel recognizes the power AI has to transform society and industries. We are committed to democratizing AI and machine-learning innovations so that everyone has the opportunity to benefit. To that end, we've been doing a number of things: This group focuses on solutions that make it easy to incorporate custom AI solutions into existing infrastructure.

The past year or so has seen a true explosion in both the capabilities and adoption of artificial intelligence technologies. Today's generalized AI tools can solve specific problems more powerfully than the complex rule-based tools that preceded them. And, because these new AI tools can be deployed in many contexts, more and more applications and industries are ripe for transformation with AI technologies. By drawing from the best posts on the O'Reilly AI blog, this in-depth report summarizes the current state of AI technologies and applications, and provides useful guides to help you get started with deep learning and other AI tools.

In this tutorial, taken from Hands-on Deep Learning with Theano by Dan Van Boxel, we'll be exploring recurrent neural networks. We'll start off by looking at the basics, before looking at RNNs through a motivating weather modeling problem. We'll also implement and train an RNN in TensorFlow. In a typical model, you have some X input features and some Y output you want to predict. We usually consider our different training samples as independent observations.

Summary: Which is more important, the data or the algorithms? This chicken and egg question led me to realize that it's the data, and specifically the way we store and process the data that has dominated data science over the last 10 years. And it all leads back to Hadoop. Recently I was challenged to speak on the role of data in data science. This almost sounds like a chicken and egg problem.

From looking at the figure above, noise suppression looks simple enough: just three conceptually simple tasks and we're done, right? Any undergrad EE student can write a noise suppression algorithm that works... kinda... sometimes. The hard part is to make it work well, all the time, for all kinds of noise. That requires very careful tuning of every knob in the algorithm, many special cases for strange signals and lots of testing. There's always some weird signal that will cause problems and require more tuning and it's very easy to break more things than you fix.

This paper examines the speaker identification potential of breath sounds in continuous speech. Speech is largely produced during exhalation. In order to replenish air in the lungs, speakers must periodically inhale. When inhalation occurs in the midst of continuous speech, it is generally through the mouth. Intra-speech breathing behavior has been the subject of much study, including the patterns, cadence, and variations in energy levels. However, an often ignored characteristic is the {\em sound} produced during the inhalation phase of this cycle. Intra-speech inhalation is rapid and energetic, performed with open mouth and glottis, effectively exposing the entire vocal tract to enable maximum intake of air. This results in vocal tract resonances evoked by turbulence that are characteristic of the speaker's speech-producing apparatus. Consequently, the sounds of inhalation are expected to carry information about the speaker's identity. Moreover, unlike other spoken sounds which are subject to active control, inhalation sounds are generally more natural and less affected by voluntary influences. The goal of this paper is to demonstrate that breath sounds are indeed bio-signatures that can be used to identify speakers. We show that these sounds by themselves can yield remarkably accurate speaker recognition with appropriate feature representations and classification frameworks.

FusionGAN is a novel genre fusion framework for music generation that integrates the strengths of generative adversarial networks and dual learning. In particular, the proposed method offers a dual learning extension that can effectively integrate the styles of the given domains. To efficiently quantify the difference among diverse domains and avoid the vanishing gradient issue, FusionGAN provides a Wasserstein based metric to approximate the distance between the target domain and the existing domains. Adopting the Wasserstein distance, a new domain is created by combining the patterns of the existing domains using adversarial learning. Experimental results on public music datasets demonstrated that our approach could effectively merge two genres.

This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural-network approximations of the underlying Koopman operator. Extended Dynamic Mode Decomposition (EDMD) provides a useful data-driven approximation of the Koopman operator for analyzing dynamical systems. This paper addresses a fundamental problem associated with EDMD: a trade-off between representational capacity of the dictionary and over-fitting due to insufficient data. A new neural network architecture combining an autoencoder with linear recurrent dynamics in the encoded state is used to learn a low-dimensional and highly informative Koopman-invariant subspace of observables. A method is also presented for balanced model reduction of over-specified EDMD systems in feature space. Nonlinear reconstruction using partially linear multi-kernel regression aims to improve reconstruction accuracy from the low-dimensional state when the data has complex but intrinsically low-dimensional structure. The techniques demonstrate the ability to identify Koopman eigenfunctions of the unforced Duffing equation, create accurate low-dimensional models of an unstable cylinder wake flow, and make short-time predictions of the chaotic Kuramoto-Sivashinsky equation.

This article demonstrates that convolutional operation can be converted to matrix multiplication, which has the same calculation way with fully connected layer. The article is helpful for the beginners of the neural network to understand how fully connected layer and the convolutional layer work in the backend. To be concise and to make the article more readable, we only consider the linear case. It can be extended to the non-linear case easily through plugging in a non-linear encapsulation to the values like this $\sigma(x)$ denoted as $x^{\prime}$.