Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable their energy-efficient design for resource-constrained scenarios (like embedded systems, IoT-Edge, etc.). We propose SpikeDyn, a comprehensive framework for energy-efficient SNNs with continual and unsupervised learning capabilities in dynamic environments, for both the training and inference phases. It is achieved through the following multiple diverse mechanisms: 1) reduction of neuronal operations, by replacing the inhibitory neurons with direct lateral inhibitions; 2) a memory- and energy-constrained SNN model search algorithm that employs analytical models to estimate the memory footprint and energy consumption of different candidate SNN models and selects a Pareto-optimal SNN model; and 3) a lightweight continual and unsupervised learning algorithm that employs adaptive learning rates, adaptive membrane threshold potential, weight decay, and reduction of spurious updates. Our experimental results show that, for a network with 400 excitatory neurons, our SpikeDyn reduces the energy consumption on average by 51% for training and by 37% for inference, as compared to the state-of-the-art. Due to the improved learning algorithm, SpikeDyn provides on avg. 21% accuracy improvement over the state-of-the-art, for classifying the most recently learned task, and by 8% on average for the previously learned tasks.

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments. Though researchers have attempted to use metrics (e.g., perplexity, BLEU) in language generation tasks or some model-based reinforcement learning methods (e.g., self-play evaluation) for automatic evaluation, these methods only show a very weak correlation with the actual human evaluation in practice. To bridge such a gap, we propose a new framework named ENIGMA for estimating human evaluation scores based on recent advances of off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation, making automatic evaluations feasible. More importantly, ENIGMA is model-free and agnostic to the behavior policies for collecting the experience data (see details in Section 2), which significantly alleviates the technical difficulties of modeling complex dialogue environments and human behaviors. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.

This listing marks 20 years since we started compiling an yearly choice of the year's most important technology. Some, for example mRNA vaccines, are already transforming our own lives, while some continue to be a couple of decades off. Below, you will get a brief description along with a link to a feature article that probes every technology in detail. We hope you will enjoy and research --taken collectively, we think this listing reflects a glimpse into our collective potential . Tech businesses have been shown to be poor stewards of their private information.

With the development of new communication technologies, the amount of data transmission has increased gradually. To satisfy this increasing computing resource demand effectively, the number of data center networks (DCNs), which are structures composed of servers connected with well‐organized‐switches, has increased worldwide. However, traditional switches do not efficiently satisfy the needs of DCNs. In recent years, an emerging networking architecture software‐defined network (SDN) has been proposed to manage the DCNs to control network switches and to deploy new network protocols. However, the main challenge in DCNs is to balance the load among servers.

Imagine looking for the optimal configuration to build an organic solar cell made from different polymers. Does the active layer need to be very thick, or very thin? Does it need a large or a small amount of each polymer? Knowing how to predict the specific composition and cell design that would result in optimum performance is one of the greatest unresolved problems in materials science. This is, in part, due to the fact that the device performance depends on multiple factors.

MECOMS is an IT solution provider specialised in the utility sector and focused on Microsoft and Azure technologies. We're investigating how artificial intelligence can help the different players in the utility market run their business processes in a more efficient way, using different techniques like machine learning and advanced chatbots. For distribution grid operators, we see interesting opportunities in the area of machine learning. We came up with the idea of using machine learning to help run the process of validation of meter readings that arrive as raw data at the IT system. Machine learning could be used to observe whether there is a consistent pattern in the reasons why meter readings run into validation errors.

Artificial intelligence (AI) has been a hot topic for a while now. While it might appear to be a fairly new concept, it's actually been around since the first computer was built back in the 1930s. The concept of AI involves machine learning. Computers could learn and act on data sets without any human programming. Essentially, AI is a computer mimicking the human brain.

In the first of our two AI-themed live online events, we invite four guest speakers working at the forefront of AI to share their exciting work. Learn about the vast applications of AI, the underlying innovative technologies and gain valuable insights on how you can build successful careers in this arena. Be inspired by their fascinating stories ranging from founding the company, product development, conducting research studies and seeking partnerships for the business. Our free-for-all event will include a presentation by our guest speakers followed by a Q&A session which will be led by SIU hosts. Please register via EventBrite to reserve a spot.

With tech giants pouring billions of dollars into artificial intelligence projects, it's hard to see how startups can find their place and create successful business models that leverage AI. However, while fiercely competitive, the AI space is also constantly causing fundamental shifts in many sectors. And this creates the perfect environment for fast-thinking and -moving startups to carve a niche for themselves before the big players move in. Last week, technology analysis firm CB Insights published an update on the status of its list of top 100 AI startups of 2020 (in case you don't know, CB Insight publishes a list of 100 most promising AI startups every year). Out of the hundred startups, four have made exits, with three going public and one being acquired by Facebook.

Traditional seismic processing workflows (SPW) are expensive, requiring over a year of human and computational effort. Deep learning (DL) based data-driven seismic workflows (DSPW) hold the potential to reduce these timelines to a few minutes. Raw seismic data (terabytes) and required subsurface prediction (gigabytes) are enormous. This large-scale, spatially irregular time-series data poses seismic data ingestion (SDI) as an unconventional yet fundamental problem in DSPW. Current DL research is limited to small-scale simplified synthetic datasets as they treat seismic data like images and process them with convolution networks. Real seismic data, however, is at least 5D. Applying 5D convolutions to this scale is computationally prohibitive. Moreover, raw seismic data is highly unstructured and hence inherently non-image like. We propose a fundamental shift to move away from convolutions and introduce SESDI: Set Embedding based SDI approach. SESDI first breaks down the mammoth task of large-scale prediction into an efficient compact auxiliary task. SESDI gracefully incorporates irregularities in data with its novel model architecture. We believe SESDI is the first successful demonstration of end-to-end learning on real seismic data. SESDI achieves SSIM of over 0.8 on velocity inversion task on real proprietary data from the Gulf of Mexico and outperforms the state-of-the-art U-Net model on synthetic datasets.