Mfine, an AI health care startup headquartered in Bangalore, today announced that it has raised $17.2 million in a series B funding round led by Japan-based venture group SBI Investment, with participation from SBI Ven Capital, Beenext, Stellaris Venture Partners, and Prime Venture Partners. This comes after a $4.2 million series A round in May 2018 and brings Mfine's total raised to $24 million, according to Crunchbase. CEO and cofounder Prasad Kompalli says the funds will be used to acquire new customers and expand service across India. "We believe that India will leapfrog the methods of health care delivery that were adopted in the developed nations, and mobile will be at the center of this disruption. The current funding is an endorsement to Mfine's unique model of working with reputed and accredited hospitals and using technology to make quality health care accessible to millions of people," he said.

Intelligence should be "distributed" where "knowledge" is created and "decisions" are made A few years ago, it was hard to find anyone to have a serious discussion about Artificial Intelligence (AI) outside academic institutions. Like any new major technology trend, the new wave of making AI and intelligent systems a reality is creating curiosity and enthusiasm. People are jumping on its bandwagon adding not only great ideas but also in many cases a lot of false promises and sometimes misleading opinions. Built by giant thinkers and academic researchers, AI adoption by industries and further development in academia around the globe is progressing at a faster rate than anyone had excepted. Accelerated by the strong belief that our biological limitations are increasingly becoming a major obstacle towards creating smart systems and machines that work with us to better use our biological cognitive capabilities to achieve higher goals. This is driving an overwhelming wave of demands and investments across industries to apply AI technologies to solve real-world problems and create smarter machines and new businesses.

New York: Researchers have developed an Artificial Intelligence (AI)-based computer programme that can help diagnose post-traumatic stress disorder (PTSD) in veterans by analysing their voices. The study, published in the journal Depression and Anxiety, found that an AI tool can distinguish with 89 per cent accuracy between the voices of those with or without PTSD. "Our findings suggest that speech-based characteristics can be used to diagnose this disease, and with further refinement and validation, may be employed in the clinic in the near future," said co-author Charles R. Marmar, Professor at NYU School of Medicine. For the study, the research team used a statistical/Machine Learning (ML) technique, called random forests, that has the ability to "learn" how to classify individuals based on examples. Such AI programmes build "decision" rules and mathematical models that enable decision-making with increasing accuracy as the amount of training data grows.

The American space agency's InSight lander appears to have detected its first seismic event on Mars. The faint rumble was picked up by the probe's sensors on 6 April - the 128th Martian day, or sol, of the mission. It is the first seismic signal detected on the surface of a planetary body other than the Earth and its Moon. Scientists say the source for this "Marsquake" could either be movement in a crack inside the planet or the shaking from a meteorite impact. Nasa's InSight probe touched down on the Red Planet in November last year. It aims to identify multiple quakes, to help build a clearer picture of Mars' interior structure.

It sounds like a subway train rushing by. But it's something much more exotic: in all likelihood, the first "marsquake" ever recorded by humans. NASA's InSight mission detected the quake on April 6, four months after the lander's highly sensitive seismometer was installed on the Martian surface. The instrument had previously registered the howling winds of the red planet and the motions of the lander's robotic arm. But the shaking picked up this month is believed to be the first quake from Mars' interior.

Background and Purpose: A current algorithm to obtain a synthetic myelin volume fraction map (SyMVF) from rapid simultaneous relaxometry imaging (RSRI) has a potential problem, that it does not incorporate information from surrounding pixels. The purpose of this study was to develop a method that utilizes a convolutional neural network (CNN) to overcome this problem. Methods: RSRI and magnetization transfer images from 20 healthy volunteers were included. A CNN was trained to reconstruct RSRI-related metric maps into a myelin volume-related index (generated myelin volume index: GenMVI) map using the myelin volume index map calculated from magnetization transfer images (MTMVI) as reference. The SyMVF and GenMVI maps were statistically compared by testing how well they correlated with the MTMVI map. The correlations were evaluated based on: (i) averaged values obtained from 164 atlas-based ROIs, and (ii) pixel-based comparison for ROIs defined in four different tissue types (cortical and subcortical gray matter, white matter, and whole brain). Results: For atlas-based ROIs, the overall correlation with the MTMVI map was higher for the GenMVI map than for the SyMVF map. In the pixel-based comparison, correlation with the MTMVI map was stronger for the GenMVI map than for the SyMVF map, and the difference in the distribution for the volunteers was significant (Wilcoxon sign-rank test, P<.001) in all tissue types. Conclusion: The proposed method is useful, as it can incorporate more specific information about local tissue properties than the existing method.

Data driven soft sensor design has recently gained immense popularity, due to advances in sensory devices, and a growing interest in data mining. While partial least squares (PLS) is traditionally used in the process literature for designing soft sensors, the statistical literature has focused on sparse learners, such as Lasso and relevance vector machine (RVM), to solve the high dimensional data problem. In the current study, predictive performances of three regression techniques, PLS, Lasso and RVM were assessed and compared under various offline and online soft sensing scenarios applied on datasets from five real industrial plants, and a simulated process. In offline learning, predictions of RVM and Lasso were found to be superior to those of PLS when a large number of time-lagged predictors were used. Online prediction results gave a slightly more complicated picture. It was found that the minimum prediction error achieved by PLS under moving window (MW), or just-in-time learning scheme was decreased up to ~5-10% using Lasso, or RVM. However, when a small MW size was used, or the optimum number of PLS components was as low as ~1, prediction performance of PLS surpassed RVM, which was found to yield occasional unstable predictions. PLS and Lasso models constructed via online parameter tuning generally did not yield better predictions compared to those constructed via offline tuning. We present evidence to suggest that retaining a large portion of the available process measurement data in the predictor matrix, instead of preselecting variables, would be more advantageous for sparse learners in increasing prediction accuracy. As a result, Lasso is recommended as a better substitute for PLS in soft sensors; while performance of RVM should be validated before online application.

Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recognition in dyadic conversations. In contrast to existing approaches, our work introduces a novel attention mechanism capable of inferring the immensity of the effect of each past utterance on the current speaker emotional state. The proposed attention mechanism performs this inference procedure without the need of a decoder network; this is achieved by means of innovative self-attention arguments. Our self-attention networks capture the correlation patterns among consecutive encoder network states, thus allowing to robustly and effectively model temporal dynamics over arbitrary long temporal horizons. Thus, we enable capturing strong affective patterns over the course of long discussions. We exhibit the effectiveness of our approach considering the challenging IEMOCAP benchmark. As we show, our devised methodology outperforms state-of-the-art alternatives and commonly used approaches, giving rise to promising new research directions in the context of Online Social Network (OSN) analysis tasks.

We propose a systematic construction of native Banach spaces for general spline-admissible operators ${\rm L}$. In short, the native space for ${\rm L}$ and the (dual) norm $\|\cdot\|_{\mathcal{X}'}$ is the largest space of functions $f: \mathbb{R}^d \to \mathbb{R}$ such that $\|{\rm L} f\|_{\mathcal{X}'}<\infty$, subject to the constraint that the growth-restricted null space of ${\rm L}$be finite-dimensional. This space, denoted by $\mathcal{X}'_{\rm L}$, is specified as the dual of the pre-native space $\mathcal{X}_{\rm L}$, which is itself obtained through a suitable completion process. The main difference with prior constructions (e.g., reproducing kernel Hilbert spaces) is that our approach involves test functions rather than sums of atoms (e.g, kernels), which makes it applicable to a much broader class of norms, including total variation. Under specific admissibility and compatibility hypotheses, we lay out the direct-sum topology of $\mathcal{X}_{\rm L}$ and $\mathcal{X}'_{\rm L}$, and identify the whole family of equivalent norms. Our construction ensures that the native space and its pre-dual are endowed with a fundamental Schwartz-Banach property. In practical terms, this means that $\mathcal{X}'_{\rm L}$ is rich enough to reproduce any function with an arbitrary degree of precision.

Architecture optimization is a promising technique to find an efficient neural network to meet certain requirements, which is usually a problem of selections. This paper introduces a concept of a trainable gate function and proposes a channel pruning method which finds automatically the optimal combination of channels using a simple gradient descent training procedure. The trainable gate function, which confers a differentiable property to discrete-valued variables, allows us to directly optimize loss functions that include discrete values such as the number of parameters or FLOPs that are generally non-differentiable. Channel pruning can be applied simply by appending trainable gate functions to each intermediate output tensor followed by fine-tuning the overall model, using any gradient-based training methods. Our experiments show that the proposed method can achieve better compression results on various models. For instance, our proposed method compresses ResNet-56 on CIFAR-10 dataset by half in terms of the number of FLOPs without accuracy drop.