Abstract--Recently, there is increasing interest and research on the interpretability of machine learning models, for example how they transform and internally represent EEG signals in Brain-Computer Interface (BCI) applications. This can help to understand the limits of the model and how it may be improved, in addition to possibly provide insight about the data itself. Schirrmeister et al. (2017) have recently reported promising results for EEG decoding with deep convolutional neural networks (ConvNets) trained in an end-to-end manner and, with a causal visualization approach, showed that they learn to use spectral amplitude changes in the input. In this study, we investigate how ConvNets represent spectral features through the sequence of intermediate stages of the network. We show higher sensitivity to EEG phase features at earlier stages and higher sensitivity to EEG amplitude features at later stages. Intriguingly, we observed a specialization of individual stages of the network to the classical EEG frequency bands alpha, beta, and high gamma. Furthermore, we find first evidence that particularly in the last convolutional layer, the network learns to detect more complex oscillatory patterns beyond spectral phase and amplitude, reminiscent of the representation of complex visual features in later layers of ConvNets in computer vision tasks. Our findings thus provide insights into how ConvNets hierarchically represent spectral EEG features in their intermediate layers and suggest that ConvNets can exploit and might help to better understand the compositional structure of EEG time series.

Reza Bosagh Zadeh is Founder CEO at Matroid and Adjunct Professor at Stanford University. His work focuses on Machine Learning, Distributed Computing, and Discrete Applied Mathematics. Reza received his PhD in Computational Mathematics from Stanford University under the supervision of Gunnar Carlsson. His awards include a KDD Best Paper Award and the Gene Golub Outstanding Thesis Award. He has served on the Technical Advisory Boards of Microsoft and Databricks.

Key sectors of interest include Internet of Things, FinTech, Future of Work, Logis-cs/Transporta-on, eHealth, Security and others. BootstrapLabs is a Venture Capital firm based in Silicon Valley and focused on Applied Ar:ficial Intelligence About Us 3. Community of Founders, Intrapreneurs, AI/ML Experts, Execu-ves, Professors, Researchers, Investors focused on Innova-on, Technology and Entrepreneurship 30K PEOPLE Our Community 200K FOLLOWERS 1K ATTENDEES Our online community between BootstrapLabs core team and its closer advisors has over 200K followers. We see traffic on our website and deal flow referral coming from over 60 countries BootstrapLabs brought together over 1,000 people during 2016. Our community is a key pillar of our success and we organize many exclusive private and public AI centric events each year 4. Applied AI Digest #1 2016 Google's DeepMind Beats a Top Player at the Game of Go Zucks to create AI-Powered Jarvis JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC IBM Watson Head on the Future of AI Read Full Articles 5. Applied AI Digest #2 Artificial Intelligence Deals on the RiseCould AI Solve the World's Biggest Problems? Harvard is building an AI Engine as fast as the Brain Read Full Articles 6. Applied AI Digest #3 Is Big Data Still a Thing?

Hard to believe that it's only been a year since I was doing the previous end-of-year round up. So much has happened in the world of AI that it is hard to fit in a couple of paragraphs. Don't expect too many details, but do expect a lot of links to follow up on them. If I have to pick my main highlight of the year, that has to go to AlphaGo Zero (paper). Not only does this new approach improve in some of the most promising directions (e.g.

In this article, I will share my findings on creating a character-based Sequence-to-Sequence model (Seq2Seq) and I will share some of the results I have found. All of this is just a tiny part of my Master Thesis and it took quite a while for me to learn how to convert the theoretical concepts into practical models. I will also share the lessons that I have learned. This blog post is about Natural Language Processing (NLP in short). It is not easy for computers to interpret texts.

During a 2016 simulation exercise, researchers evaluated the ability of 32 different deep learning algorithms to detect lymph node metastases in patients with breast cancer. Each algorithm's performance was then compared to that of a panel of 11 pathologists with time constraint (WTC). Overall, the team found that seven of the algorithms outperformed the panel of pathologists, publishing an in-depth analysis in JAMA. "To our knowledge, this is the first study that shows that interpretation of pathology images can be performed by deep learning algorithms at an accuracy level that rivals human performance," wrote lead author Babak Ehteshami Bejnordi, MS, Radboud University Medical Center in Nijmegen, the Netherlands, and colleagues. The simulation took place during the Cancer Metastases in Lymph Nodes Challenge 2016 (CAMELYON16) in the Netherlands.

It's an approximation, face-swapped to look like she's performing in an existing incest-themed porn video. The video was created with a machine learning algorithm, using easily accessible materials and open-source code that anyone with a working knowledge of deep learning algorithms could put together. A clip from the full video, hosted on SendVids, showing Gal Gadot's face on a porn star's body. It's not going to fool anyone who looks closely. Sometimes the face doesn't track correctly and there's an uncanny valley effect at play, but at a glance it seems believable.

Professor of Artificial Intelligence Wolfgang Faber comments on Google announcing that its AlphaGo Zero artificial intelligence program has triumphed at chess against world-leading specialist software within hours of teaching itself the game from scratch and considers where humans will start losing their jobs to intelligent computers and machines. "'Google's'superhuman' DeepMind AI claims chess crown' has been a headline on the BBC recently. What does it mean, and are our jobs, or even our lives in danger? First, let us have a look at what caused this headline: A few days ago, a manuscript by a group around David Silver, Thomas Hubert, and Julian Schrittwieser of London-based, Google (or rather Alphabet)-owned DeepMind was uploaded to arXiv, in which the system AlphaZero is described and very impressive results in learning how to play three traditional board games (chess, shogi, Go) well are reported. The setup allowed for learning very successful (superhuman) strategies in a few ...

In this article, I will share my findings on creating a character-based Sequence-to-Sequence model (Seq2Seq) and I will share some of the results I have found. All of this is just a tiny part of my Master Thesis and it took quite a while for me to learn how to convert the theoretical concepts into practical models. I will also share the lessons that I have learned. This blog post is about Natural Language Processing (NLP in short). It is not easy for computers to interpret texts.

Have you ever heard of a term called'Deep Learning'? Well, deep learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. Artificial Intelligence (AI) has come up with the concept of chatbots or computer algorithms that simulate a human conversation to hire new employees, act as an HR executive and answer questions, or personalize learning experience. So, hunting, recruiting, or streamlining employee assessment processes; machine learning and AI can make it easier for HR personnel to perform their jobs in a better way. Let us see some scenarios where AI and AI professionals have worked together to hire new talent, manage various tasks, and improve employee satisfaction.