The discovery of novel inhibitor molecules for emerging drug-target proteins is widely acknowledged as a challenging inverse design problem: Exhaustive exploration of the vast chemical search space is impractical, especially when the target structure or active molecules are unknown. Here we validate experimentally the broad utility of a deep generative framework trained at-scale on protein sequences, small molecules, and their mutual interactions -- that is unbiased toward any specific target. As demonstrators, we consider two dissimilar and relevant SARS-CoV-2 targets: the main protease and the spike protein (receptor binding domain, RBD). To perform target-aware design of novel inhibitor molecules, a protein sequence-conditioned sampling on the generative foundation model is performed. Despite using only the target sequence information, and without performing any target-specific adaptation of the generative model, micromolar-level inhibition was observed in in vitro experiments for two candidates out of only four synthesized for each target. The most potent spike RBD inhibitor also exhibited activity against several variants in live virus neutralization assays. These results therefore establish that a single, broadly deployable generative foundation model for accelerated hit discovery is effective and efficient, even in the most general case where neither target structure nor binder information is available.

The success of supervised deep learning models in medical image segmentation relies on detailed annotations. However, labor-intensive manual labeling is costly and inefficient, especially in dense object segmentation. To this end, we propose a self-supervised learning based approach with a Prior Self-activation Module (PSM) that generates self-activation maps from the input images to avoid labeling costs and further produce pseudo masks for the downstream task. To be specific, we firstly train a neural network using self-supervised learning and utilize the gradient information in the shallow layers of the network to generate self-activation maps. Afterwards, a semantic-guided generator is then introduced as a pipeline to transform visual representations from PSM to pixel-level semantic pseudo masks for downstream tasks. Furthermore, a two-stage training module, consisting of a nuclei detection network and a nuclei segmentation network, is adopted to achieve the final segmentation. Experimental results show the effectiveness on two public pathological datasets. Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations.

Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation. While the ideal dataset for imitation learning is homogenous and low-variance -- reflecting a single, optimal method for performing a task -- natural human behavior has a great deal of heterogeneity, with several optimal ways to demonstrate a task. This multimodality is inconsequential to human users, with task variations manifesting as subconscious choices; for example, reaching down, then across to grasp an object, versus reaching across, then down. Yet, this mismatch presents a problem for interactive imitation learning, where sequences of users improve on a policy by iteratively collecting new, possibly conflicting demonstrations. To combat this problem of demonstrator incompatibility, this work designs an approach for 1) measuring the compatibility of a new demonstration given a base policy, and 2) actively eliciting more compatible demonstrations from new users. Across two simulation tasks requiring long-horizon, dexterous manipulation and a real-world "food plating" task with a Franka Emika Panda arm, we show that we can both identify incompatible demonstrations via post-hoc filtering, and apply our compatibility measure to actively elicit compatible demonstrations from new users, leading to improved task success rates across simulated and real environments.

Label distribution learning can characterize the polysemy of an instance through label distributions. However, some noise and uncertainty may be introduced into the label space when processing label distribution data due to artificial or environmental factors. To alleviate this problem, we propose a \textbf{L}abel \textbf{C}orrelation \textbf{G}rid (LCG) to model the uncertainty of label relationships. Specifically, we compute a covariance matrix for the label space in the training set to represent the relationships between labels, then model the information distribution (Gaussian distribution function) for each element in the covariance matrix to obtain an LCG. Finally, our network learns the LCG to accurately estimate the label distribution for each instance. In addition, we propose a label distribution projection algorithm as a regularization term in the model training process. Extensive experiments verify the effectiveness of our method on several real benchmarks.

Dr. Andrew Ng is a globally recognized leader in AI. He is Founder and CEO of DeepLearning.AI, Founder and CEO of Landing AI, General Partner at AI Fund, Chairman and Co-Founder of Coursera and an Adjunct Professor at Stanford University's Computer Science Department. He has authored or co-authored over 200 research papers in machine learning, robotics and related fields. In 2013, he was named to the Time 100 list of the most influential persons in the world.

Artificial intelligence (AI) is beginning to have a significant impact on the global online sports betting industry. Sportsbooks are able to provide more precise odds and forecasts due to AI, which can assist bettors place more profitable wagers. AI can also assist in identifying future problem gamblers and preventing them from accruing excessive debt. Sportsbooks can identify warning indicators and provide support to individuals who require it by utilising AI to track betting trends and monitor betting patterns. Overall, AI is enhancing everyone's enjoyment and fairness in the field of online sports betting.

The 11th of October marks Ada Lovelace Day, a special moment in the annual tech calendar. It's an International Day of Recognition that celebrates women in STEM, named after the woman widely recognised as the world's first computer programmer. So immense was Ada Lovelace's contribution in a short life -- she died of illness in 1842 at age 36 -- that her notes provided inspiration for Alan Turing's work on the first modern computers in the 1940s. Ada Lovelace Day provides an opportunity to reflect. Our minds have travelled back not as far as the 1800s but to May this year when we hosted a panel at the Girls in Tech Australia Conference.

Ruban Thanigasalam (centre, right) has used a robotic surgical system for 15 years, and says it benefits patients and surgeons.Credit: Ken Leanfore The COVID-19 pandemic has stretched health-care workforces around the world to their limits, as illness and burnout extract a toll from clinicians, nurses and staff. The need for innovations that can reduce workloads is pressing and has intensified interest in artificial intelligence (AI) and robotics as potential technologies to help in many ways, from processing doctors' notes, to improving surgical outcomes, and even assisting clinicians with rapid decision-making during crises. Cancer diagnosis and treatment have been especially affected by the pandemic, as hospital resources are diverted to urgent infectious-disease outbreaks, and health-care staff are ill or in isolation. Many of the key pressure points in this field are tasks that lend themselves to innovative solutions using AI and robotics. One of these is image processing for cancer screening and diagnosis; for example, checking mammograms.

Laguna Hills, Calif. – DATE, 2022 – BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world's first commercial producer of ultra-low power neuromorphic AI IP, has extended the breadth and depth of its neuromorphic IP with two new patents granted by the US Patents and Trademarks Office (USPTO), and the acquisition of previously licensed technology from Toulouse Tech Transfer (TTT). These latest additions of technical assets reinforce BrainChip's event-based processor differentiation for high performance, ultra-low power AI inference and on-chip learning. BrainChip also acquired full ownership of the IP rights related to JAST learning rule and algorithms from French technology transfer-based company TTT, including issued patent EP3324344 and pending patents US2019/0286944 and EP3324343. The invention related to the acquired IP rights include pattern detection algorithms that provide BrainChip with significant competitive advantages. The company held an exclusive license for the IP prior to their acquisition.

This study presents a new approach to metaphorical paraphrase generation by masking literal tokens of literal sentences and unmasking them with metaphorical language models. Unlike similar studies, the proposed algorithm does not only focus on verbs but also on nouns and adjectives. Despite the fact that the transfer rate for the former is the highest (56%), the transfer of the latter is feasible (24% and 31%). Human evaluation showed that our system-generated metaphors are considered more creative and metaphorical than human-generated ones while when using our transferred metaphors for data augmentation improves the state of the art in metaphorical sentence classification by 3% in F1.