Cisco on Monday debuted a series of software enhancements designed to put AI and machine learning deeper into the network. Key features include new network automation and analytics tools that are meant to help enterprise IT teams glean more insights and visibility from network data. On the visibility side, new machine learning features collect relevant data from local networks and correlates it against aggregate deidentified data, creating individualized network baselines that constantly adapt as more devices, users and apps are added. Meanwhile, Cisco's ML is also correlating network data against baselines to uncover potential network issues and alert IT before problems occur. Cisco is also touting new machine-reasoning algorithms for improved troubleshooting, giving IT admins and network engineers the ability to detect and correct issues and vulnerabilities more quickly.

Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities. Hot spots easily appear in road intersections, where effective communication among vehicles is challenging. UAVs may serve as relays with the advantages of low price, easy deployment, line-of-sight links, and flexible mobility. In this paper, we study a UAV-assisted vehicular network where the UAV jointly adjusts its transmission power and bandwidth allocation under 3D flight to maximize the total throughput. First, we formulate a Markov Decision Process (MDP) problem by modeling the mobility of vehicles and the state transitions caused by the UAV's 3D flight. Secondly, we solve the target problem using a deep reinforcement learning method, namely, the deep deterministic policy gradient, and propose three solutions with different control objectives. Thirdly, in a simplified model with small state and action spaces, we verify the optimality of proposed algorithms. Comparing with two baseline schemes, we demonstrate the effectiveness of proposed algorithms in a realistic model.

Traffic classification has various applications in today's Internet, from resource allocation, billing and QoS purposes in ISPs to firewall and malware detection in clients. Classical machine learning algorithms and deep learning models have been widely used to solve the traffic classification task. However, training such models requires a large amount of labeled data. Labeling data is often the most difficult and time-consuming process in building a classifier. To solve this challenge, we reformulate the traffic classification into a multi-task learning framework where bandwidth requirement and duration of a flow are predicted along with the traffic class. The motivation of this approach is twofold: First, bandwidth requirement and duration are useful in many applications, including routing, resource allocation, and QoS provisioning. Second, these two values can be obtained from each flow easily without the need for human labeling or capturing flows in a controlled and isolated environment. We show that with a large amount of easily obtainable data samples for bandwidth and duration prediction tasks, and only a few data samples for the traffic classification task, one can achieve high accuracy. We conduct two experiment with ISCX and QUIC public datasets and show the efficacy of our approach.

Consider a device that is connected to an edge processor via a communication channel. The device holds local data that is to be offloaded to the edge processor so as to train a machine learning model, e.g., for regression or classification. Transmission of the data to the learning processor, as well as training based on Stochastic Gradient Descent (SGD), must be both completed within a time limit. Assuming that communication and computation can be pipelined, this letter investigates the optimal choice for the packet payload size, given the overhead of each data packet transmission and the ratio between the computation and the communication rates. This amounts to a tradeoff between bias and variance, since communicating the entire data set first reduces the bias of the training process but it may not leave sufficient time for learning. Analytical bounds on the expected optimality gap are derived so as to enable an effective optimization, which is validated in numerical results.

Scattering transforms are non-trainable deep convolutional architectures that exploit the multi-scale resolution of a wavelet filter bank to obtain an appropriate representation of data. More importantly, they are proven invariant to translations, and stable to perturbations that are close to translations. This stability property dons the scattering transform with a robustness to small changes in the metric domain of the data. When considering network data, regular convolutions do not hold since the data domain presents an irregular structure given by the network topology. In this work, we extend scattering transforms to network data by using multiresolution graph wavelets, whose computation can be obtained by means of graph convolutions. Furthermore, we prove that the resulting graph scattering transforms are stable to metric perturbations of the underlying network. This renders graph scattering transforms robust to changes on the network topology, making it particularly useful for cases of transfer learning, topology estimation or time-varying graphs.

Opportunistic communications are expected to playa crucial role in enabling context-aware vehicular services. A widely investigated opportunistic communication paradigm for storing a piece of content probabilistically in a geographica larea is Floating Content (FC). A key issue in the practical deployment of FC is how to tune content replication and caching in a way which achieves a target performance (in terms of the mean fraction of users possessing the content in a given region of space) while minimizing the use of bandwidth and host memory. Fully distributed, distance-based approaches prove highly inefficient, and may not meet the performance target,while centralized, model-based approaches do not perform well in realistic, inhomogeneous settings. In this work, we present a data-driven centralized approach to resource-efficient, QoS-aware dynamic management of FC.We propose a Deep Learning strategy, which employs a Convolutional Neural Network (CNN) to capture the relationships between patterns of users mobility, of content diffusion and replication, and FC performance in terms of resource utilization and of content availability within a given area. Numerical evaluations show the effectiveness of our approach in deriving strategies which efficiently modulate the FC operation in space and effectively adapt to mobility pattern changes over time.

Cisco helps IT teams better understand network behavior and predict issues with new artificial intelligence and machine learning capabilities. Since its introduction two years ago, Cisco's intent-based networking has reinvented how networks are built and managed. Cisco is furthering this effort through multidomain integrations designed to provide end-to-end security, segmentation and application experience. Cisco is delivering these new software advancements via software subscriptions, granting customers access to ongoing innovation. SAN DIEGO, California – Cisco Live U.S. – Today, Cisco announces software innovations designed to make managing and securing networks easier.

Artificial emotional intelligence, or "emotion AI," is emerging as a key component of the broader AI movement. The general idea is this: It's all very well having machines that can understand and respond to natural-language questions, and even beat humans at games, but until they can decipher non-verbal cues such as vocal intonations, body language, and facial expressions, humans will always have the upper hand in understanding other humans. And it's against that backdrop that countless companies are working toward improving computer vision and voice analysis techniques, to help machines detect the intricate and finely balanced emotions of a flesh-and-bones homo sapiens. One of those companies is Realeyes, a company that helps big brands such as AT&T, Mars, Hershey's, and Coca-Cola gauge human emotions through desktop computers' and mobile devices' cameras. The London-based startup, which was founded in 2007, today announced a fresh $12.4 million round of funding from Draper Esprit, the VC arm of Japanese telecom giant NTT Docomo, Japanese VC fund Global Brain, Karma Ventures, and The Entrepreneurs Fund.

Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the varying demands and the allocated bandwidth as the environment state and the action, respectively. However, allocating bandwidth in a finer resolution usually implies larger action space, and unfortunately DQL fails to quickly converge in this case. In this paper, we introduce discrete normalized advantage functions (DNAF) into DQL, by separating the $\mathcal{Q}$-value function as a state-value function term and an advantage term and exploiting a deterministic policy gradient descent (DPGD) algorithm to avoid the unnecessary calculation of $\mathcal{Q}$-value for every state-action pair. Furthermore, as DPGD only works in continuous action space, we embed a k-nearest neighbor algorithm into DQL to quickly find a valid action in the discrete space nearest to the DPGD output. Finally, we verify the faster convergence of the DNAF-based DQL through extensive simulations.

In their work to unearth evidence of fraudulent activities, forensic accounting investigators dig through diverse data looking for anomalies that suggest something is just not right. But as the massive volumes of data collected by companies balloon, this task has become increasingly arduous, time-consuming and humanly impossible. Instead of investigators manually reviewing spreadsheet rows and columns, looking for three or four data elements that together indicate a suspicious transaction, ML can peruse thousands of data elements -- instantly. The regrettable consequence is the greater chance of a well-thought-out scam slipping through the cracks. A case in point is healthcare fraud, which has been estimated to cost the United States tens of billions of dollars annually.