"There is no better place to explore the overlap between machine learning and computational neuroscience than the annual NeurIPS event," said Yoshihisa Yamamoto, PHI Lab Director. "We are excited to see the latest paper by Dr. Tanaka and his Stanford colleagues, as well as those by our colleagues at the NTT Software Innovation Center and NTT Communication Science Laboratories and expect the fields of neural networking and machine learning will benefit from the efficiencies and expanded capabilities that they are proposing." This year's seven-day virtual NeurIPS event includes an expo, conference sessions, tutorials and workshops. The authors of these papers will participate in the event through poster and short recorded presentations. A follow-up to the "Pruning Neural Networks" paper, as noted above, will be presented at one of the event's workshops.

Seika, a town located in the southern part of the Kyoto Prefecture, has a mascot anime girl character named Seika Kyomachi. The mascot is notable for employing various technological innovations in her mission to spread information about the town; she became a Voiceroid character in 2016, her 3D data is open source, and in July she became a Virtual YouTuber. Her latest foray is into artificial intelligence, which would allow her to respond to queries in real time. The "Narikiri AI" (Impersonation AI) project is a collaboration between the city of Seikai and NTT Communication Science Laboratories. The AI will be developed by taking feedback from a small group of users who are knowledgeable about the town and the mascot; they provide sample questions and answers, as well as vote on responses that sound the most in-character for the mascot.

SEIKA, Kyoto Prefecture--Fans of the adorable Seika Kyomachi, the town of Seika's popular mascot, will soon be able to carry on a conversation with the digital character. The small town, located between Kyoto and Nara, is collaborating with NTT Communication Science Laboratories to develop artificial intelligence capabilities for the mascot. The plan would allow Seika Kyomachi to answer questions from visitors and locals about tourism and municipal administration. Seika officials announced the project in July, and aim to put the AI-driven character into practical use in November. The town introduced Seika Kyomachi as its official mascot in 2013 and has long pioneered new ways to use the cute character.

Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing a dynamic Bayesian network to predict the likelihood of where humans typically focus on a video scene. The proposed model is composed of a dynamic Bayesian network with 4 layers. Our model provides a framework that simulates and combines the visual saliency response and the cognitive state of a person to estimate the most probable attended regions. Sample-based inference with Markov chain Monte-Carlo based particle filter and stream processing with multi-core processors enable us to estimate human visual attention in near real time. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic models.