Neural network pruning is a popular method to reduce the size of a trained model, allowing efficient computation during inference time, with minimal loss in accura cy. However, such a method still requires the process of training an over-parameterized network, as trai ning a pruned network from scratch seems to fail (see [ 10 ]). Recently, a work by Frankle and Carbin [ 10 ] has presented a surprising phenomenon: pruned neural networks can be trained to achieve good performance, when resetting their weights to their initial values. Hence, the authors state the lottery ticket hypothesis: a randomly-initialized neural network contains a subnetwork such that, when trained in isolation, can match the performance of the original network. This observation has attracted great interest, with variou s followup works trying to understand this intriguing phenomenon. Specifically, very recent works by Z hou et al. [ 37 ], Ramanujan et al. [ 27 ] presented algorithms to find subnetworks that already achieve good per formance, without any training.

--Federated Learning (FL) is viewed as a promising technique for future distributed machine learning. It permits a large number of mobile devices participating in the training of a global model collaboratively without having to expose their local private data. Although the challenge of the network connection will be much relieved in 5G/B5G era, the training latency is still an obstacle preventing FL from being largely adopted. One of the most fundamental problems that leads to large training latency is the bad candidate-selection of FL participants. T o the best of our knowledge, the existing candidate-selection algorithms belong to the reactive manner . Under such reactive selection, the FL parameter server only knows the currently-observed resources of all candidates. In the dynamic FL environment, the mobile devices selected by the reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL. T o this end, we study the proactive candidate-selection for FL in this paper . We first let each candidate device locally predict the qualities of both its training and reporting phases using the LSTM network. Then, the proposed candidate-selection algorithm is implemented by the Deep Reinforcement Learning (DRL) framework, which can adapt to the dynamically varying factors in the metropolitan edge computing environment. Finally, the real-world trace-driven experiments prove that the proposed proactive approach outperforms the existing reactive algorithms with respect to the ratio of valid participants and the test accuracy of the aggregated global FL model. Federated Learning (FL) [1], [2] is a branch of distributed machine learning that enables a group of distributed devices to train their individual local models using the local dataset. Thus, FL is a promising computing paradigm in our future intelligent life, especially under the fifth generation (5G) and the beyond (B5G) communications networks. For example, the FederatedAveraging (FedAvg) algorithm [1] can help mobile users predict the next-words when users are using the Google's GBoard [3] in their smartphones. To realize a large-scale federated learning framework, a number of challenges must be addressed.

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to compare and evaluate. In this paper, we aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. For example, we obtain a better understanding of generalization properties, and we can readily transfer well-understood techniques, such as model ensemble, pre-training, joint training, data augmentation, and even nearest neighbor based methods. We provide an intuitive analogy of these methods in the context of meta-learning and show that they give rise to significant improvements in model performance on few-shot learning.

During the past decade, many anomaly detection approaches have been introduced in different fields such as network monitoring, fraud detection, and intrusion detection. However, they require understanding of data pattern and often need a long off-line period to build a model or network for the target data. Providing real-time and proactive anomaly detection for streaming time series without human intervention and domain knowledge is highly valuable since it greatly reduces human effort and enables appropriate countermeasures to be undertaken before a disastrous damage, failure, or other harmful event occurs. However, this issue has not been well studied yet. To address it, this paper proposes RePAD, which is a Real-time Proactive Anomaly Detection algorithm for streaming time series based on Long Short-Term Memory (LSTM). RePAD utilizes short-term historic data points to predict and determine whether or not the upcoming data point is a sign that an anomaly is likely to happen in the near future. By dynamically adjusting the detection threshold over time, RePAD is able to tolerate minor pattern change in time series and detect anomalies either proactively or on time. Experiments based on two time series datasets collected from the Numenta Anomaly Benchmark demonstrate that RePAD is able to proactively detect anomalies and provide early warnings in real time without human intervention and domain knowledge.

Dubins tours represent a solution of the Dubins Traveling Salesman Problem (DTSP) that is a variant of the optimization routing problem to determine a curvature-constrained shortest path to visit a set of locations such that the path is feasible for Dubins vehicle, which moves only forward and has a limited turning radius. The DTSP combines the NP-hard combinatorial optimization to determine the optimal sequence of visits to the locations, as in the regular TSP, with the continuous optimization of the heading angles at the locations, where the optimal heading values depend on the sequence of visits and vice versa. We address the computationally challenging DTSP by fast evaluation of the sequence of visits by the proposed Windowing Surrogate Model (WiSM) which estimates the length of the optimal Dubins path connecting a sequence of locations in a Dubins tour. The estimation is sped up by a regression model trained using close to optimum solutions of small Dubins tours that are generalized for large-scale instances of the addressed DTSP utilizing the sliding window technique and a cache for already computed results. The reported results support that the proposed WiSM enables a fast convergence of a relatively simple evolutionary algorithm to high-quality solutions of the DTSP. We show that with an increasing number of locations, our algorithm scales significantly better than other state-of-the-art DTSP solvers.

It might come as a surprising fact that there are presently 14 Chinese AI organizations valued at $1 billion. These unicorns worth consolidated comes to $40.5 billion, as per a report China Money Network released during the World Economic Forum's Summer Davos gathering in Beijing. Just to place these numbers in context. Google purchased DeepMind for over $500 million in 2014. Chinese voice recognition giant iFlytek Co. has a market capitalization of 63 billion yuan ($9.2 billion).

Shelly Duvall is hiding from her crazed husband as he chops down the door with an axe. Jim Carrey sticks his head through the opening and cackles the iconic line: "Here's Johnny!" What you're seeing is not a Hollywood special effect. It wasn't done with After Effects, green screen, or with costuming and makeup. The video is a fake created by deep learning artificial intelligence – a deepfake.

Artificial Intelligence is one of the hottest field in computer science at the moment and has taken the world by storm as a major field of development and research. Python has emerged as a dominant language in AI/ML programming because of its simplicity and flexibility. Are you a Python developer who is interested to build real-world Artificial Intelligence applications? If so, A-Z Artificial Intelligence with Python is for you! This comprehensive 5-in-1 training course is designed such that you can add an intelligence layer to any application that's based on images, text, stock market, or some other form of data.

An effort to use voice-assistant devices like Amazon's Alexa to detect signs of memory problems in people has gotten a boost with a grant from the federal government. Researchers from Dartmouth-Hitchcock and the University of Massachusetts Boston will get a four-year $1.2 million grant from the National Institute on Aging. The team hopes to develop a system that would use machine and deep learning techniques to detect changes in speech patterns to determine if someone is a risk of developing dementia or Alzheimer's. "We are tackling a significant and complicated data-science question: whether the collection of long-term speech patterns of individuals at home will enable us to develop new speech-analysis methods for early detection of this challenging disease," Xiaohui Liang, an assistant professor of computer science from the University of Massachusetts Boston, said in a statement. "Our team envisions that the changes in the speech patterns of individuals using the voice assistant systems may be sensitive to their decline in memory and function over time."

Dr. Dong Yu is a principal researcher at Microsoft Research. His research has been focusing on speech recognition and applications of machine learning techniques. He has published two monographs and over 150 papers in these areas and is the inventor/co-inventor of near 60 granted/pending patents. His recent work on the context-dependent deep neural network hidden Markov model (CD-DNN-HMM), which was recognized by the IEEE SPS 2013 best paper award, caused a paradigm shift on large vocabulary speech recognition. Dr. Dong Yu is currently serving as a member of the IEEE Speech and Language Processing Technical Committee (2013-).