Is artificial intelligence the new alchemy? That is, are the powerful algorithms that control so much of our lives -- from internet searches to social media feeds -- the modern equivalent of turning lead into gold? Moreover: Would that be such a bad thing? According to the prominent AI researcher Ali Rahimi and others, today's fashionable neural networks and deep learning techniques are based on a collection of tricks, topped with a good dash of optimism, rather than systematic analysis. Modern engineers, the thinking goes, assemble their codes with the same wishful thinking and misunderstanding that the ancient alchemists had when mixing their magic potions.

Recently, a team led by clinicians at Beth Israel Deaconess Medical Center and Harvard Medical School demonstrated that an artificial intelligence (AI)-based computer vision system can enhance screening accuracy of colon cancer. Tyler M Berzin, a gastroenterologist from Beth Israel Deaconess Medical Center, discusses how AI-based computer-vision algorithms can assist physicians. Let us examine how this is accomplished. According to Tyler, this would be a real-time application of artificial intelligence, which is also rather unique. In clinical medicine, the majority of examples of AI applications occur after the initial patient engagement, for example, during the subsequent evaluation of the X-ray.

In part 1, I compared surface patterns that are recognized today in technologies like deep learning, with deep patterns that are brain-like: storing the meaning of signs, not just the semiotic signs themselves. As brains deal with variation effortlessly, it makes sense that language embraces such variation, too.

It's a comment I've seen hundreds of times, or variations of throughout my time here at Kotaku: internet complaints about the quality of reviews. "A bot can do better than this," some would cry. So let's put that to the test. I've run this test before, although last time I fed Kotaku Australia comments into the machine learning model. That was run using a free online version of the GPT-2 language model, although the more powerful GPT-3 model is available now if you're willing to pay to access the API. So I did that, specifically through a tool called Shortly. We got some fun responses last time the AI pretended to double as a commenter.

Brent Davis, CEO of NomadXR, shares his thoughts on how we can create deep connections using artificial intelligence, deep learning, and virtual twins within the oncoming Metaverse.

For something so effortless and automatic, vision is a tough job for the brain. It's remarkable that we can transform electromagnetic radiation--light--into a meaningful world of objects and scenes. After all, light focused into an eye is merely a stream of photons with different wave properties, projecting continuously on our retinas, a layer of cells on the backside of our eyes. Before it's transduced by our eyes, light has no brightness or color, which are properties of animal perception. Our retinas transform this energy into electrical impulses that propagate within our nervous system. Somehow this comes out as a world: skies, children, art, auroras, and occasionally ghosts and UFOs.

Attention based models such as Transformers involve pairwise interactions between data points, modeled with a learnable attention matrix. Importantly, this attention matrix is normalized with the SoftMax operator, which makes it row-wise stochastic. In this paper, we propose instead to use Sinkhorn's algorithm to make attention matrices doubly stochastic. We call the resulting model a Sinkformer. We show that the row-wise stochastic attention matrices in classical Transformers get close to doubly stochastic matrices as the number of epochs increases, justifying the use of Sinkhorn normalization as an informative prior. On the theoretical side, we show that, unlike the SoftMax operation, this normalization makes it possible to understand the iterations of self-attention modules as a discretized gradient-flow for the Wasserstein metric. We also show in the infinite number of samples limit that, when rescaling both attention matrices and depth, Sinkformers operate a heat diffusion. On the experimental side, we show that Sinkformers enhance model accuracy in vision and natural language processing tasks. In particular, on 3D shapes classification, Sinkformers lead to a significant improvement.

High-power particle accelerators are complex machines with thousands of pieces of equipmentthat are frequently running at the cutting edge of technology. In order to improve the day-to-dayoperations and maximize the delivery of the science, new analytical techniques are being exploredfor anomaly detection, classification, and prognostications. As such, we describe the applicationof an uncertainty aware Machine Learning method, the Siamese neural network model, to predictupcoming errant beam pulses using the data from a single monitoring device. By predicting theupcoming failure, we can stop the accelerator before damage occurs. We describe the acceleratoroperation, related Machine Learning research, the prediction performance required to abort beamwhile maintaining operations, the monitoring device and its data, and the Siamese method andits results. These results show that the researched method can be applied to improve acceleratoroperations.

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for downstream tasks. We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE), to extract and separate the static (time-invariant) and dynamic (time-variant) factors in the latent space. Different from previous sequential variational autoencoder methods, we use a novel evidence lower bound which maximizes the mutual information between the input and the latent factors, while penalizes the mutual information between the static and dynamic factors. We leverage contrastive estimations of the mutual information terms in training, together with simple yet effective augmentation techniques, to introduce additional inductive biases. Our experiments show that C-DSVAE significantly outperforms the previous state-of-the-art methods on multiple metrics.

Given the current momentum and progress, ADS can be expected to continue to advance as variety of ADS products are going to become commercially available in the space of a decade (Chan, 2017). It is envisioned that automated driving technology will lead to a paradigm shift in transportation systems in terms of user experience, mode choices and business models. Nowadays, a greater number of industrialists are increasing their investments in self-driving cars technologies and, more generally, in the automotive sector. ADS research and an increasing number of industrial implementations have been catalyzed by the accumulated knowledge in vehicle dynamics in the wake of breakthroughs in computer vision caused by the advent of deep learning (Krizhevsky, Sutskever, and Hinton, 2012; Bojarski, Yeres, Choromanaska, Choromanski, Firner, Jackel, and Muller, 2017; Kocić, Jovičić, and Drndarević, 2019; Li, Yang, Qu, Cao, and Li, 2021a) and the availability of new sensor modalities such as lidar (Schwarz, 2010). Deep Learning (DL) has been widely used for the implementation of ADSs.