Neural Audio Synthesis (NAS) models offer interactive musical control over high-quality, expressive audio generators. While these models can operate in real-time, they often suffer from high latency, making them unsuitable for intimate musical interaction. The impact of architectural choices in deep learning models on audio latency remains largely unexplored in the NAS literature. In this work, we investigate the sources of latency and jitter typically found in interactive NAS models. We then apply this analysis to the task of timbre transfer using RAVE, a convolutional variational autoencoder for audio waveforms introduced by Caillon et al. in 2021. Finally, we present an iterative design approach for optimizing latency. This culminates with a model we call BRAVE (Bravely Realtime Audio Variational autoEncoder), which is low-latency and exhibits better pitch and loudness replication while showing timbre modification capabilities similar to RAVE. We implement it in a specialized inference framework for low-latency, real-time inference and present a proof-of-concept audio plugin compatible with audio signals from musical instruments. We expect the challenges and guidelines described in this document to support NAS researchers in designing models for low-latency inference from the ground up, enriching the landscape of possibilities for musicians.

State estimation is an essential component of autonomous systems, usually relying on sensor fusion that integrates data from cameras, LiDARs and IMUs. Recently, radars have shown the potential to improve the accuracy and robustness of state estimation and perception, especially in challenging environmental conditions such as adverse weather and low-light scenarios. In this paper, we present a framework for ego-velocity estimation, which we call RAVE, that relies on 3D automotive radar data and encompasses zero velocity detection, outlier rejection, and velocity estimation. In addition, we propose a simple filtering method to discard infeasible ego-velocity estimates. We also conduct a systematic analysis of how different existing outlier rejection techniques and optimization loss functions impact estimation accuracy. Our evaluation on three open-source datasets demonstrates the effectiveness of the proposed filter and a significant positive impact of RAVE on the odometry accuracy. Furthermore, we release an open-source implementation of the proposed framework for radar ego-velocity estimation accompanied with a ROS interface.

The first few steps on the path toward living forever alongside the longevity enthusiast Bryan Johnson are straightforward: "Go to bed on time, eat healthy food, and exercise," he told a crowd in Brooklyn on Saturday morning. "But to start, you guys are now going to do a breathing exercise." He directed the 100-plus people gathered around him to put their hands on the shoulders of their neighbors, forming a series of concentric circles; he then counted as we inhaled and exhaled in unison. I had arrived at a bouldering gym for the first in a series of events held that day by Johnson, a 46-year-old centimillionaire who made his fortune in Silicon Valley but is best known for waging a war on death that he claims to be winning. His ambitions are somehow greater, and more science-fictional, than those of other biohackers and life-extension fanatics--a group that includes Peter Thiel, Jeff Bezos, and Mark Zuckerberg.

AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play. Many researchers are looking for ways to reproduce and improve results for other games/tasks. However, the architecture is designed to learn from scratch, tabula rasa, accepting a cold-start problem in self-play. Recently, a warm-start enhancement method for Monte Carlo Tree Search was proposed to improve the self-play starting phase. It employs a fixed parameter $I^\prime$ to control the warm-start length. Improved performance was reported in small board games. In this paper we present results with an adaptive switch method. Experiments show that our approach works better than the fixed $I^\prime$, especially for "deep," tactical, games (Othello and Connect Four). We conjecture that the adaptive value for $I^\prime$ is also influenced by the size of the game, and that on average $I^\prime$ will increase with game size. We conclude that AlphaZero-like deep reinforcement learning benefits from adaptive rollout based warm-start, as Rapid Action Value Estimate did for rollout-based reinforcement learning 15 years ago.

Eight people have now been fined up to £10,000 after an illegal rave that attracted 3,000 people, with arrests also made for public order offences and driving under the influence of drugs. The unlicensed event at Banwen, on the edge of the Brecon Beacons, started Saturday night. There were still 400 people at the site on Monday morning. South Wales Police Assistant Chief Constable Dave Thorne said drone footage would help identify organisers. A student who attended the rave admitted being taken aback by the scale of the event and likened it to a festival.

Recently, AlphaZero has achieved landmark results in deep reinforcement learning, by providing a single self-play architecture that learned three different games at super human level. AlphaZero is a large and complicated system with many parameters, and success requires much compute power and fine-tuning. Reproducing results in other games is a challenge, and many researchers are looking for ways to improve results while reducing computational demands. AlphaZero's design is purely based on self-play and makes no use of labeled expert data or domain specific enhancements; it is designed to learn from scratch. We propose a novel approach to deal with this cold-start problem by employing simple search enhancements at the beginning phase of self-play training, namely Rollout, Rapid Action Value Estimate (RAVE) and dynamically weighted combinations of these with the neural network, and Rolling Horizon Evolutionary Algorithms (RHEA). Our experiments indicate that most of these enhancements improve the performance of their baseline player in three different (small) board games, with especially RAVE based variants playing strongly.

If the barrel-shaped JBL Xtreme 2 that Scott Wilkinson reviewed a couple weeks back is ready to party, Sony's cubist SRS-XB501G smart speaker is equipped to deliver a crowd-pleasing LED light show at a backyard rave. A young crowd, that is. Color-shifting LED light bars run around the perimeter of the speaker's face, and there's a pair of independent white LEDs in the top middle. A second white LED sits above the woofer. Sony says these lights can be synchronized to the music you're listening to, and there are no fewer than six light modes for you to choose from (rave, chill, hot, cool, strobe, and random flash).

Artificially intelligence is now making its way into every aspect of your digital lives. While most companies cannot stop talking about what they've done in the field, there are a host of cutting-edge AI-powered websites that are useful for everyday tasks today. Here are several awesome and insightful artificial intelligence sites you probably don't know about. PixelDrive is a cloud storage platform which employs a set of machine learning algorithms What Are Machine Learning Algorithms? Here's How They Work What Are Machine Learning Algorithms?

Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree search, while a deep neural network generalises those plans. Subsequently, tree search is improved by using the neural network policy to guide search, increasing the strength of new plans. In contrast, standard deep Reinforcement Learning algorithms rely on a neural network not only to generalise plans, but to discover them too. We show that ExIt outperforms REINFORCE for training a neural network to play the board game Hex, and our final tree search agent, trained tabula rasa, defeats MoHex 1.0, the most recent Olympiad Champion player to be publicly released.

Monte Carlo Tree Search (MCTS) is the state of the art algorithm for many games including the game of Go and General Game Playing (GGP). The standard algorithm for MCTS is Upper Confidence bounds applied to Trees (UCT). For games such as Go a big improvement over UCT is the Rapid Action Value Estimation (RAVE) heuristic. We propose to generalize the RAVE heuristic so as to have more accurate estimates near the leaves. We test the resulting algorithm named GRAVE for Atarigo, Knighthrough, Domineering and Go.