Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes. Recent studies followed a non-adaptive setting, where the seed nodes are selected before the start of the diffusion process and network parameters are updated when the diffusion stops. We consider an adaptive version of content-dependent online influence maximization problem where the seed nodes are sequentially activated based on real-time feedback. In this paper, we formulate the problem as an infinite-horizon discounted MDP under a linear diffusion process and present a model-based reinforcement learning solution. Our algorithm maintains a network model estimate and selects seed users adaptively, exploring the social network while improving the optimal policy optimistically. We establish $\widetilde O(\sqrt{T})$ regret bound for our algorithm. Empirical evaluations on synthetic network demonstrate the efficiency of our algorithm.

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation is a popular compression technique that can reduce the resource needs of such models, where a large teacher model transfers knowledge to a small student model. To drastically reduce memory requirements and energy consumption, we propose two extensions for a popular sentence-transformer distillation procedure: generation of an optimal size vocabulary and dimensionality reduction of the embedding dimension of teachers prior to distillation. We evaluate these extensions on two different types of ranker models. This results in extremely compressed student models whose analysis on a test dataset shows the significance and utility of our proposed extensions.

British-born Andrew Ng has had a rich career in the technology industry as Co-Founder and Head of Google Brain, former Chief Scientist at Baidu and Co-Founder of Coursera. At Baidu, Ng built the company's artificial intelligence (AI) sector into a team of several people. In an interview with Lex Fridman, Ng shared where his passion for the industry started: " Growing up in Hong Kong and Singapore, I started learning to code when I was five or six years old. At that time I was learning the BASIC programming language and they would take these folks and they'll tell you type this program into your computer." "So I typed out programs on my computer and as the result of all the typing, I would get to play these very simple, shoot them up games that I had implemented on my little computer. So I thought it was fascinating as a young kid that I could write this code. I was really just copying code from a book into my computer to then play these cool little video games. Another moment for me was when I was a teenager and my father was a doctor was reading about expert systems and about neural networks. So he got me to read some of these books and I thought it was really cool that you could write a computer that started to exhibit intelligence." he continued.

Amidst the rise in hybrid working and the Great Resignation, employers understand that they must provide a competitive employee experience to attract, and crucially, to retain top talent. This should go hand in hand with digital transformation initiatives. Tangible benefits and salary alone are no longer sufficient to differentiate the employer brand and employee experience. Employers need to create a stronger emotional connection with employees to ensure they are engaged and connected with the organisation. As personalisation becomes ubiquitous, businesses must embrace an array of innovative digital tools to make the employee experience seamless.

Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user terminal) and feeding back to the transmitter. The overhead of CSI feedback occupies substantial uplink bandwidth resources, especially when the number of the transmit antennas is large. Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. In this paper, a comprehensive overview of state-of-the-art research on this topic is provided, beginning with basic DL concepts widely used in CSI feedback and then categorizing and describing some existing DL-based feedback works. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy. Works on bit-level CSI feedback and joint design of CSI feedback with other communication modules are also introduced, and some practical issues, including training dataset collection, online training, complexity, generalization, and standardization effect, are discussed. At the end of the paper, some challenges and potential research directions associated with DL-based CSI feedback in future wireless communication systems are identified.

Quantum neural networks are promising for a wide range of applications in the Noisy Intermediate-Scale Quantum era. As such, there is an increasing demand for automatic quantum neural architecture search. We tackle this challenge by designing a quantum circuits metric for Bayesian optimization with Gaussian process. To this goal, we propose a new quantum gates distance that characterizes the gates' action over every quantum state and provide a theoretical perspective on its geometrical properties. Our approach significantly outperforms the benchmark on three empirical quantum machine learning problems including training a quantum generative adversarial network, solving combinatorial optimization in the MaxCut problem, and simulating quantum Fourier transform. Our method can be extended to characterize behaviors of various quantum machine learning models.

The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to represent the scalar field using a multi-centered atomic basis analogous to that routinely used in density fitting approximations. However, the non-orthogonality of the basis poses challenges for the learning exercise, as it requires accounting for all the atomic density components at once. We devise a gradient-based approach to directly minimize the loss function of the regression problem in an optimized and highly sparse feature space. In so doing, we overcome the limitations associated with adopting an atom-centered model to learn the electron density over arbitrarily complex datasets, obtaining extremely accurate predictions. The enhanced framework is tested on 32-molecule periodic cells of liquid water, presenting enough complexity to require an optimal balance between accuracy and computational efficiency. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom with respect to the reference density functional calculations. Finally, we test our method on the highly heterogeneous QM9 benchmark dataset, showing that a small fraction of the training data is enough to derive ground-state total energies within chemical accuracy.

When summer begins, all of us get excited and start planning all the fun activities that we would like to do in these a few days. Some of us, love to focus on upskill and upgrade ourselves in terms of skillset. We are happy to announce that Analytics Vidhya is launching a summer training programme for ML enthusiasts. Machine learning applications are around us everywhere. For example, when you're typing a simple email, you notice suggestions appear.

Can I get a certificate after completing the course? Are there any other coupons available for this course? Note: 100% OFF Udemy coupon codes are valid for maximum 3 days only. Look for "ENROLL NOW" button at the end of the post. Disclosure: This post may contain affiliate links and we may get small commission if you make a purchase.

Kids walk into kindergarten with big dreams for themselves -- writing their names, making friends, and if they're lucky, maybe even learning about new species of dinosaurs. Though they may not express it this way, young children see school as the key to unlocking their potential, the first step to becoming an astronaut, a veterinarian, a firefighter or whatever they aspire to be when they grow up. Their families, too, have high hopes for what the next 13 years will bring, counting on educators to prepare their children for the future cognitively, socially and emotionally. But unfortunately in many classrooms across the U.S., these kids and their families discover that the education system's goals for them are much less ambitious than their own. Throughout elementary school, then into middle and high school, students are guided to academic milestones that are simply too low, targets that should be baselines rather than ceilings.