This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep invertible density estimators called normalizing flows, to model the dictionary in a linear decomposition method such as NMF, effectively creating a bijection between the space of dictionary elements and the associated probability space, allowing a differentiable search through the dictionary space, guided by the estimated densities. As the initial formulation was a proof of concept with some practical limitations, we will present several steps towards making it scalable, hoping to improve both the computational complexity of the method and its signal decomposition capabilities. As a testbed for experimental evaluation, we choose the task of frame-level piano transcription, where the signal is to be decomposed into sources whose activity is attributed to individual piano notes. To highlight the impact of improved non-linear modelling of sources, we compare variants of our method to a linear overcomplete NMF baseline. Experimental results will show that even in the absence of additional constraints, our models produce increasingly sparse and precise decompositions, according to two pertinent evaluation measures.

The efficiency of using the YOLOV5 machine learning model for solving the problem of automatic de-tection and recognition of micro-objects in the marine environment is studied. Samples of microplankton and microplastics were prepared, according to which a database of classified images was collected for training an image recognition neural network. The results of experiments using a trained network to find micro-objects in photo and video images in real time are presented. Experimental studies have shown high efficiency, comparable to manual recognition, of the proposed model in solving problems of detect-ing micro-objects in the marine environment.

I'm the anti-hero Taylor Swift sings about. I listen to the same song over and over and over again, scratching that part of my brain that just loves every moment of it. Luckily for me, this Cyber Monday, there are speaker deals from Sonos and Google that will sound good with every replay. Luckily for my husband, friends, and anyone else in my vicinity, there are also plenty of deals on headphones from our favorite brands, like Jabra, Apple, and Beats, to drown my tunes out. If you're looking to listen to whatever you want with the best sound possible, we've assembled all the best Cyber Monday headphone and speaker deals here. Updated November 27: We've added new deals on headphones from Bose and Bang & Olufsen.

It's a great time to upgrade your home theater thanks to some excellent Cyber Monday TV and soundbar deals. If you've yet to take the plunge to a modern 4K TV, or you are still listening to your favorite shows and movies through those tinny built-in TV speakers, there are massive reasons to upgrade. Modern home theater technology now has better backlighting, sharper resolution, and immersive surround sound for less money required than ever before. Go on, convert your living room into a mini cinema. Updated November 27: We've added deals on HBO Max and TVs from Hisense.

I recently caught up with Ian Hogarth and Nathan Benaich, who each year produce The State of AI Report, a must-read snapshot of how commercial applications of A.I. are evolving. Benaich is the founder of Air Street Capital, a solo venture capital fund that is one of the savviest early-stage investors in A.I.-based startups I know. Hogarth is the former co-founder of concert discovery app Songkick and has since go on to become a prominent angel investor as well one of the founders behind the founder-lead European venture capital platform Plural. There's always a lot to digest in their report. But one of the key takeaways from this year's State of AI is that concerns established tech giants and their affiliated A.I. research labs would monopolize the development of A.I. have been proven, if not exactly wrong, then at least premature. While it is true that Alphabet (which has both Google Brain and Deepmind in its stable), Meta, Microsoft, and OpenAI (which is closely partnered now with Microsoft) are building large "foundational models" for natural language processing and image and video generation, they are hardly the only players in the game.

Jaron Lanier, the eminent American computer scientist, composer and artist, is no stranger to skepticism around social media, but his current interpretations of its effects are becoming darker and his warnings more trenchant. Lanier, a dreadlocked free-thinker credited with coining the term "virtual reality", has long sounded dire sirens about the dangers of a world over-reliant on the internet and at the increasing mercy of tech lords, their social media platforms and those who work for them. Nothing about the last few weeks – of chaos on Twitter and the ever-increasing spread of conspiracy theory and disinformation – has changed that. The current state of the tech industry is ripe with danger and poses an existential threat, he believes. "People survive by passing information between themselves," Lanier, 61, told the Guardian in an interview.

A number of commentators have argued in recent years that the media overemphasises negativity in its content. Answering this question is no trivial matter, as it requires a standard against which the media's coverage can be compared. That is, it is challenging to establish how negative or positive media content should be. What we can certainly determine instead is how the sentiment (positive or negative) and emotional undertones (such as fear, anger or joy) of news content compare with the same metrics at different points in time. This allows us to establish whether news media content is becoming more positive over time, more negative or pretty much staying the same.

Neural Networks (NNs), or Artificial Neural Networks (ANNs), started as a big promise, and their models were quite simple compared to the models we have today: it was a simple neuron with binary outputs based on thresholds. In layman terms, it would read values as input, sum them weighted by parameters (called learning weights, where the knowledge is stored), and compared to a threshold: if it is higher, the output is one (it simulated the firing of a neuron in biology, which follows similar patterns). Except for the big hope people placed on them, they could, and still, can only separate binary boundaries: yes or no, sick or no, guilty or no. Nonetheless, do not fall prey to the common trap that simplicity as being easy: boundaries can be hard even for complex decision processes, such as release or not a patient under healthcare, or release or not a prisoner after some appeals to do so. From one side, we had some people from neuroscience seeing on the models possible explanations for their biological phenomena (i.e., in silico simulations, it was quite appealing that we could simplify the brain workings using such a simple model, based on summations). On the other hand, applied mathematical and computer scientists looking for new solutions for their complex problems out of the box (e.g., XOR problem[1], it is a problem simple for humans, but hard for machines).

Heterogeneous information networks (HINs) are widely employed for describing real-world data with intricate entities and relationships. To automatically utilize their semantic information, graph neural architecture search has recently been developed on various tasks of HINs. Existing works, on the other hand, show weaknesses in instability and inflexibility. To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs. Specifically, to learn how graph neural networks (GNNs) propagate messages along various types of edges, PMMM adopts an efficient differentiable framework to search for a meaningful meta multigraph, which can capture more flexible and complex semantic relations than a meta graph. The differentiable search typically suffers from performance instability, so we further propose a stable algorithm called partial message search to ensure that the searched meta multigraph consistently surpasses the manually designed meta-structures, i.e., meta-paths. Extensive experiments on six benchmark datasets over two representative tasks, including node classification and recommendation, demonstrate the effectiveness of the proposed method. Our approach outperforms the state-of-the-art heterogeneous GNNs, finds out meaningful meta multigraphs, and is significantly more stable.

Multi-view attributed graph clustering is an important approach to partition multi-view data based on the attribute feature and adjacent matrices from different views. Some attempts have been made in utilizing Graph Neural Network (GNN), which have achieved promising clustering performance. Despite this, few of them pay attention to the inherent specific information embedded in multiple views. Meanwhile, they are incapable of recovering the latent high-level representation from the low-level ones, greatly limiting the downstream clustering performance. To fill these gaps, a novel Dual Information enhanced multi-view Attributed Graph Clustering (DIAGC) method is proposed in this paper. Specifically, the proposed method introduces the Specific Information Reconstruction (SIR) module to disentangle the explorations of the consensus and specific information from multiple views, which enables GCN to capture the more essential low-level representations. Besides, the Mutual Information Maximization (MIM) module maximizes the agreement between the latent high-level representation and low-level ones, and enables the high-level representation to satisfy the desired clustering structure with the help of the Self-supervised Clustering (SC) module. Extensive experiments on several real-world benchmarks demonstrate the effectiveness of the proposed DIAGC method compared with the state-of-the-art baselines.