Recent studies identified that sequential Recommendation is improved by the attention mechanism. By following this development, we propose Relation-Aware Kernelized Self-Attention (RKSA) adopting a self-attention mechanism of the Transformer with augmentation of a probabilistic model. The original self-attention of Transformer is a deterministic measure without relation-awareness. Therefore, we introduce a latent space to the self-attention, and the latent space models the recommendation context from relation as a multivariate skew-normal distribution with a kernelized covariance matrix from co-occurrences, item characteristics, and user information. This work merges the self-attention of the Transformer and the sequential recommendation by adding a probabilistic model of the recommendation task specifics. We experimented RKSA over the benchmark datasets, and RKSA shows significant improvements compared to the recent baseline models. Also, RKSA were able to produce a latent space model that answers the reasons for recommendation.

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling tasks. However, efficiently modelling long-term dependencies in these sequences is still challenging. Although the receptive field of these models grows exponentially with the number of layers, computing the convolutions over very long sequences of features in each layer is time and memory-intensive, prohibiting the use of longer receptive fields in practice. To increase efficiency, we make use of the "slow feature" hypothesis stating that many features of interest are slowly varying over time. For this, we use a U-Net architecture that computes features at multiple time-scales and adapt it to our auto-regressive scenario by making convolutions causal. We apply our model ("Seq-U-Net") to a variety of tasks including language and audio generation. In comparison to TCN and Wavenet, our network consistently saves memory and computation time, with speed-ups for training and inference of over 4x in the audio generation experiment in particular, while achieving a comparable performance in all tasks.

With opening of Doctor Sleep this past weekend, we are reminded of the visionary genius of Stanley Kubrick. His powerful impact on art, technology and, yes, even humanity itself remains. Perhaps his most profound contribution was his science-fiction masterpiece 2001: A Space Odyssey, which was produced in 1968 and was based on the novel (and previously, the short story "The Sentinel") by Arthur C. Clarke. The film explores human evolution, existentialism and, notably, artificial intelligence. This is pure visual poetry about the relationship between man and technology. In many ways, this piece of art inspired today's technology, which is now inspiring today's "art."

Fall armyworm, the larval life stage of a fall armyworm moth, impacts maize crops worldwide but particularly in countries like Uganda, where agricultural businesses employ 70% of the population. Studies show the potential impact is between 8.3 and 20.6 million tons per year, with the fallout amounting to between $2.48 million and $6.19 million per year. The threat of devastating losses prompted developers participating in a Google Developer Group in Mbale to create an Android app -- FlatButter -- that identifies signs of fall armyworm damage in maize crops. It's been featured on a national TV station in Uganda and highlighted by the Food Agricultural Organization of the United Nations, as well as by Google in a short film published today. "The vast damage and yield losses in maize production, due to FAW, got the attention of global organizations, who are calling for innovators to help," wrote Hansu Mobile and Intelligent Innovations CEO Nsubuga Hassan, who led the team that developed the app.

Amazon's Echo has been our long-time favorite in the lineup of Alexa-enabled smart speakers and displays. Since its introduction in 2015, the Echo has stood out in an increasingly congested marketplace for its sound quality, far-field voice technology, and minimal footprint. The new Echo is no exception to that trend with its improved speaker, rounded design, and ever-helpful Alexa. Let's dig a little deeper into what the third-generation Echo is about and whether you should get one. The third-generation Echo can put out decent sound with its 0.8-inch tweeter and 3-inch woofer. While you might find the Echo's entry-level smaller sibling, the Dot, appealing for its lower price point, the Echo is a reasonable place to get started with smart speakers because it manages to produce respectable sound quality for its size and sub-$100 cost.

But if the absurd meanderings of talk-show bot Merrill Grambell are any indication, Jimmy Fallon can probably rest easy. The automated persona is the freewheeling host of the recurring comedy series Deep Learning With Merrill Grambell, in which it interviews comedians, artists and other creative types with varying degrees of coherence. Even creator Will Brierly, a video game designer and comedy writer, doesn't know what will happen when his procedural generator takes the stage, most often in the form of a crudely sketched man with a pencil mustache and a genial mid-Atlantic accent projected onto a screen next to a panel of guests. "It's such a surprise for me watching the show, too," Brierly said. "You put in all this stuff that you think will probably happen or hope will happen, but you can't practice it."

One of the things I love most about data science is stumbling upon some of the coolest and most powerful tools which instantly enable me to do cool and powerful things. I recently created a Spotify developer account, learned how to scrape lyrics, learned about sentiment analysis, word clouds, and other NLP concepts, and taught myself how to use an awesome interactive data visualization software called Tableau. And, most importantly of all, I have a long list of further projects I want to tackle next. I would be remiss not to give credit to the two Medium articles that helped me stumble in a productive, ever forward-moving direction. The first one is called "Extracting Spotify data on your favourite artist via Python" by Rare Loot.

If you're like me, you have a love-hate relationship with your CRM… You know you need one, but updating it ranks right there next to "schedule exploratory root canal" on your list of things to do. This week, I have a solution. He's created a new and very unique CRM, driven by AI, so you don't have to do so much work…and your CRM stays current. Plus he shares his best insights (from studying thousands of business owners' and sales teams' habits) on what the most successful salespeople do to win business. He took his inspiration for this from the movie Her.

Pizza lunch will be provided at 12:15pm, with the talk following at 12:30pm. All students, alumni, staff and faculty are welcome to register for this free event using the registration link below. "Communication has been weaponized, used to provoke, mislead and influence the public in numerous insidious ways. Disinformation was just the first stage of an evolving trend of using information to subvert democracy, confuse rival states, define the narrative and control public opinion. Using large, unregulated, open environments that tech companies once promised would "empower" ordinary people, disinformation has spread rapidly across the globe.