In a recent work arXiv:2008.08601, Halverson, Maiti and Stoner proposed a description of neural networks in terms of a Wilsonian effective field theory. The infinite-width limit is mapped to a free field theory, while finite $N$ corrections are taken into account by interactions (non-Gaussian terms in the action). In this paper, we study two related aspects of this correspondence. First, we comment on the concepts of locality and power-counting in this context. Indeed, these usual space-time notions may not hold for neural networks (since inputs can be arbitrary), however, the renormalization group provides natural notions of locality and scaling. Moreover, we comment on several subtleties, for example, that data components may not have a permutation symmetry: in that case, we argue that random tensor field theories could provide a natural generalization. Second, we improve the perturbative Wilsonian renormalization from arXiv:2008.08601 by providing an analysis in terms of the nonperturbative renormalization group using the Wetterich-Morris equation. An important difference with usual nonperturbative RG analysis is that only the effective (IR) 2-point function is known, which requires setting the problem with care. Our aim is to provide a useful formalism to investigate neural networks behavior beyond the large-width limit (i.e.~far from Gaussian limit) in a nonperturbative fashion. A major result of our analysis is that changing the standard deviation of the neural network weight distribution can be interpreted as a renormalization flow in the space of networks. We focus on translations invariant kernels and provide preliminary numerical results.

When most folks think of Qualcomm, the first technologies that likely come to mind are the company's industry-leading mobile platform system-on-chips for smartphones, as well as the company's end-to-end 5G connectivity solutions. However, whether you consider applications like image recognition, speech input, natural language translation or recommendation engines, modern smartphone platforms typically require a lot of artificial intelligence (AI) processing horsepower as well. As such, after years of developing silicon and software platform solutions for mobile AI applications, it stands to reason that Qualcomm has an opportunity to bring its AI accelerator technology to other intelligent edge devices and the cloud. And that's just what's happening with Qualcomm's Cloud AI 100 inference accelerator portfolio, as evidenced by the company's recent joint announcement with Foxconn, one of the largest electronics contract manufacturers and ODMs in the world. Foxconn's Industrial Internet division has launched a new AI-enabled machine vision platform called Gloria.

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot topic in both industrial and academic communities. Many frameworks, such as federated learning and federated distillation, have been proposed. However, few of them takes good care of obstacles such as the time-varying topology resulted by the characteristics of wireless networks. In this paper, we propose a distributed learning framework based on a scalable deep neural network (DNN) design. By exploiting the permutation equivalence and invariance properties of the learning tasks, the DNNs with different scales for different clients can be built up based on two basic parameter sub-matrices. Further, model aggregation can also be conducted based on these two sub-matrices to improve the learning convergence and performance. Finally, simulation results verify the benefits of the proposed framework by compared with some baselines.

A great deal has been written about the technologies fueling 5G, especially how those technologies will improve the experience that users have regarding connectivity. Similarly, much has been said about how ongoing developments in technology will usher in a new generation of network-aware applications. In this article, we discuss one key aspect of 5G technology and how it will impact the development of wireless network capacity. This is one of the more important but often neglected aspects of wireless communication evolution. It represents yet another important reason why the convergence of cloud computing and wireless communications makes so much sense.

Packet routing is a fundamental problem in communication networks that decides how the packets are directed from their source nodes to their destination nodes through some intermediate nodes. With the increasing complexity of network topology and highly dynamic traffic demand, conventional model-based and rule-based routing schemes show significant limitations, due to the simplified and unrealistic model assumptions, and lack of flexibility and adaption. Adding intelligence to the network control is becoming a trend and the key to achieving high-efficiency network operation. In this paper, we develop a model-free and data-driven routing strategy by leveraging reinforcement learning (RL), where routers interact with the network and learn from the experience to make some good routing configurations for the future. Considering the graph nature of the network topology, we design a multi-agent RL framework in combination with Graph Neural Network (GNN), tailored to the routing problem. Three deployment paradigms, centralized, federated, and cooperated learning, are explored respectively. Simulation results demonstrate that our algorithm outperforms some existing benchmark algorithms in terms of packet transmission delay and affordable load.

Qualcomm said Monday that it recently acquired the assets of Twenty Billion Neurons, a Microsoft-backed artificial intelligence/computer vision startup that develops avatars that can see and interact with people in a human-like way. The San Diego mobile technology company declined to say how much it paid for TwentyBN, which has locations in Berlin and Toronto. But it is likely a relatively small deal. Qualcomm said the company has under 20 employees. It raised about $10 million in venture capital from M12 -- Microsoft's venture capital fund-- and others since it was founded in 2015 by Chief Executive Roland Memisevic. Memisevic was the co-head of MILA, a well-respected AI research institute in Montreal.

Networks are frequently used to model complex systems comprised of interacting elements. While links capture the topology of direct interactions, the true complexity of many systems originates from higher-order patterns in paths by which nodes can indirectly influence each other. Path data, representing ordered sequences of consecutive direct interactions, can be used to model these patterns. However, to avoid overfitting, such models should only consider those higher-order patterns for which the data provide sufficient statistical evidence. On the other hand, we hypothesise that network models, which capture only direct interactions, underfit higher-order patterns present in data. Consequently, both approaches are likely to misidentify influential nodes in complex networks. We contribute to this issue by proposing eight centrality measures based on MOGen, a multi-order generative model that accounts for all paths up to a maximum distance but disregards paths at higher distances. We compare MOGen-based centralities to equivalent measures for network models and path data in a prediction experiment where we aim to identify influential nodes in out-of-sample data. Our results show strong evidence supporting our hypothesis. MOGen consistently outperforms both the network model and path-based prediction. We further show that the performance difference between MOGen and the path-based approach disappears if we have sufficient observations, confirming that the error is due to overfitting.

During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in real-world deployments. This poses the need to count on new generations of students, researchers and practitioners with a solid background in ML applied to networks. During 2020, the International Telecommunication Union (ITU) has organized the "ITU AI/ML in 5G challenge'', an open global competition that has introduced to a broad audience some of the current main challenges in ML for networks. This large-scale initiative has gathered 23 different challenges proposed by network operators, equipment manufacturers and academia, and has attracted a total of 1300+ participants from 60+ countries. This paper narrates our experience organizing one of the proposed challenges: the "Graph Neural Networking Challenge 2020''. We describe the problem presented to participants, the tools and resources provided, some organization aspects and participation statistics, an outline of the top-3 awarded solutions, and a summary with some lessons learned during all this journey. As a result, this challenge leaves a curated set of educational resources openly available to anyone interested in the topic.

All the sessions from Transform 2021 are available on-demand now. With the rise of on-demand TV shows and movies, viewers have a dizzying array of entertainment options to explore. Cable provider Comcast has been helping customers navigate this expansive content landscape using AI via its Xfinity voice remote. The remote taps machine learning to help customers decide what to watch and when to watch it, providing users with a tailored at-home video experience, Comcast CTO Matthew Zelesko explained at VentureBeat's virtual Transform 2021 conference. "The content landscape has grown dramatically. And we realized that it was much harder for customers to determine even simple questions, like what to watch and where to watch it," Zelesko said.

Can machine learning help emerging markets leapfrog generations of technology to take advantage of future networks? Join a group of Nigerian academics on their quest to build a freely available speech recognition library that can function locally given the huge number of languages spoken across Africa.