Most experts have settled on a description of Artificial Intelligence as being the scientific endeavor of building computers that mimic the capabilities of the human brain. To put that into perspective, we know that Human Intelligence started to evolve 7–8 million years ago when our oldest ancestors had a brain volume of about 450 cubic centimeters. In the next 3.5 million years our ancestors' brain volume increased to about 1350 cubic centimeters. Modern humans (average brain volume of about 1200 cubic centimeters) evolved from the Homo Sapiens species during a period of dramatic climate change 300,000 years ago. Like other early humans that were living at this time, they gathered and hunted food, and evolved behaviors that helped them respond to the challenges of survival in unstable environments.

While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTData, NLCodec, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usable as a service, or as a parent model for transfer-learning to even lower-resource languages.

Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated into deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and reinforcement learning paradigms. In this paper, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks. We identify multiple aspects of biological replay that are missing in deep learning systems and hypothesize how they could be utilized to improve artificial neural networks.

We present AlphaChute: a state-of-the-art algorithm that achieves superhuman performance in the ancient game of Chutes and Ladders. We prove that our algorithm converges to the Nash equilibrium in constant time, and therefore is -- to the best of our knowledge -- the first such formal solution to this game. Surprisingly, despite all this, our implementation of AlphaChute remains relatively straightforward due to domain-specific adaptations. We provide the source code for AlphaChute here in our Appendix.

Modelers use automatic differentiation of computation graphs to implement complex Deep Learning models without defining gradient computations. However, modelers often use sampling methods to estimate intractable expectations such as in Reinforcement Learning and Variational Inference. Current methods for estimating gradients through these sampling steps are limited: They are either only applicable to continuous random variables and differentiable functions, or can only use simple but high variance score-function estimators. To overcome these limitations, we introduce Storchastic, a new framework for automatic differentiation of stochastic computation graphs. Storchastic allows the modeler to choose from a wide variety of gradient estimation methods at each sampling step, to optimally reduce the variance of the gradient estimates. Furthermore, Storchastic is provably unbiased for estimation of any-order gradients, and generalizes variance reduction techniques to higher-order gradient estimates. Finally, we implement Storchastic as a PyTorch library.

Alphas are stock prediction models capturing trading signals in a stock market. A set of effective alphas can generate weakly correlated high returns to diversify the risk. Existing alphas can be categorized into two classes: Formulaic alphas are simple algebraic expressions of scalar features, and thus can generalize well and be mined into a weakly correlated set. Machine learning alphas are data-driven models over vector and matrix features. They are more predictive than formulaic alphas, but are too complex to mine into a weakly correlated set. In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes. The new alphas predict returns with high accuracy and can be mined into a weakly correlated set. In addition, we propose a novel alpha mining framework based on AutoML, called AlphaEvolve, to generate the new alphas. To this end, we first propose operators for generating the new alphas and selectively injecting relational domain knowledge to model the relations between stocks. We then accelerate the alpha mining by proposing a pruning technique for redundant alphas. Experiments show that AlphaEvolve can evolve initial alphas into the new alphas with high returns and weak correlations.

We present a parallel machine translation training corpus for English and Akuapem Twi of 25,421 sentence pairs. We used a transformer-based translator to generate initial translations in Akuapem Twi, which were later verified and corrected where necessary by native speakers to eliminate any occurrence of translationese. In addition, 697 higher quality crowd-sourced sentences are provided for use as an evaluation set for downstream Natural Language Processing (NLP) tasks. The typical use case for the larger human-verified dataset is for further training of machine translation models in Akuapem Twi. The higher quality 697 crowd-sourced dataset is recommended as a testing dataset for machine translation of English to Twi and Twi to English models. Furthermore, the Twi part of the crowd-sourced data may also be used for other tasks, such as representation learning, classification, etc. We fine-tune the transformer translation model on the training corpus and report benchmarks on the crowd-sourced test set.

Susanne Rafelski and her colleagues had a deceptively simple goal. "We wanted to be able to label many different structures in the cell, but do live imaging," says the quantitative cell biologist and deputy director of the Allen Institute for Cell Science in Seattle, Washington. "And we wanted to do it in 3D." That kind of goal normally relies on fluorescence microscopy -- problematic in this case because, with only a handful of colours to use, the scientists would run out of labels well before they ran out of structures. Also problematic is that these reagents are pricey and laborious to use.

Google is adding more information to Search and Maps about businesses that offer options for grocery delivery and pickup. The information is getting added to search automatically, which means there's no work needed on the part of businesses, but it's an update worth being aware of. This addition to Google Search and Maps is rolling out as part of a larger update which includes a number of other useful features. We'll look at the other features at the end of this article – let's first go over the enhancements to Google My Business profiles. Google is bringing shopping information to stores' business profiles to assist people with finding convenient grocery delivery and pickup options.

Every day, militaristic and violent metaphors are used by journalists and political actors alike to communicate and mobilize action. These word choices may seem effective yet, these metaphors, imbued with violent imagery, can be dangerous. From a policy standpoint, they are also ineffective (and potentially harmful). One example is how the global "war on drugs" terminology victimized, stigmatized, and misplaced blame. As noted by others, as with any war, there are always civil rights abuses.