The latter suggests that to infer what someone means, an agent constructs a rationale for the observed behaviour of others. Communication then requires two agents labour under similar compulsions and have similar experiences (construct similar solutions to similar tasks). Any non-human intelligence may construct solutions such that any rationale for their behaviour (and thus the meaning of their signals) is outside the scope of what a human is inclined to notice or comprehend. Further, the more compressed a signal, the closer it will appear to random noise. Another intelligence may possess the ability to compress information to the extent that, to us, their signals would appear indistinguishable from noise (an explanation for The Fermi Paradox). To facilitate predictive accuracy an AGI would tend to more compressed representations of the world, making any rationale for their behaviour more difficult to comprehend for the same reason. Communication with and control of an AGI may subsequently necessitate not only human-like compulsions and experiences, but imposed cognitive impairment.

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To this end, offline RL algorithms adopt either a constraint or a penalty term that explicitly guides the policy to stay close to the given dataset. However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem. Moreover, these methods under-utilize the generalization ability of deep neural networks and often fall into suboptimal solutions too close to the given dataset. In this work, we propose an uncertainty-based offline RL method that takes into account the confidence of the Q-value prediction and does not require any estimation or sampling of the data distribution. We show that the clipped Q-learning, a technique widely used in online RL, can be leveraged to successfully penalize OOD data points with high prediction uncertainties. Surprisingly, we find that it is possible to substantially outperform existing offline RL methods on various tasks by simply increasing the number of Q-networks along with the clipped Q-learning. Based on this observation, we propose an ensemble-diversified actor-critic algorithm that reduces the number of required ensemble networks down to a tenth compared to the naive ensemble while achieving state-of-the-art performance on most of the D4RL benchmarks considered.

Black-box optimization formulations for biological sequence design have drawn recent attention due to their promising potential impact on the pharmaceutical industry. In this work, we propose to unify two seemingly distinct worlds: likelihood-free inference and black-box sequence design, under one probabilistic framework. In tandem, we provide a recipe for constructing various sequence design methods based on this framework. We show how previous drug discovery approaches can be "reinvented" in our framework, and further propose new probabilistic sequence design algorithms. Extensive experiments illustrate the benefits of the proposed methodology.

We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes. Rather than training with convex combinations of pairs of examples and their labels, we use noise-perturbed convex combinations of pairs of data points in both input and feature space. This method includes mixup and manifold mixup as special cases, but it has additional advantages, including better smoothing of decision boundaries and enabling improved model robustness. We provide theory to understand this as well as the implicit regularization effects of NFM. Our theory is supported by empirical results, demonstrating the advantage of NFM, as compared to mixup and manifold mixup. We show that residual networks and vision transformers trained with NFM have favorable trade-offs between predictive accuracy on clean data and robustness with respect to various types of data perturbation across a range of computer vision benchmark datasets.

Recent developments in large-scale machine learning suggest that by scaling up data, model size and training time properly, one might observe that improvements in pre-training would transfer favorably to most downstream tasks. In this work, we systematically study this phenomena and establish that, as we increase the upstream accuracy, the performance of downstream tasks saturates. In particular, we investigate more than 4800 experiments on Vision Transformers, MLP-Mixers and ResNets with number of parameters ranging from ten million to ten billion, trained on the largest scale of available image data (JFT, ImageNet21K) and evaluated on more than 20 downstream image recognition tasks. We propose a model for downstream performance that reflects the saturation phenomena and captures the nonlinear relationship in performance of upstream and downstream tasks. Delving deeper to understand the reasons that give rise to these phenomena, we show that the saturation behavior we observe is closely related to the way that representations evolve through the layers of the models. We showcase an even more extreme scenario where performance on upstream and downstream are at odds with each other. That is, to have a better downstream performance, we need to hurt upstream accuracy.

Background: Survival analysis concerns the study of timeline data where the event of interest may remain unobserved (i.e., censored). Studies commonly record more than one type of event, but conventional survival techniques focus on a single event type. We set out to integrate both multiple independently censored time-to-event variables as well as missing observations. Methods: An energy-based approach is taken with a bi-partite structure between latent and visible states, commonly known as harmoniums (or restricted Boltzmann machines). Results: The present harmonium is shown, both theoretically and experimentally, to capture non-linear patterns between distinct time recordings. We illustrate on real world data that, for a single time-to-event variable, our model is on par with established methods. In addition, we demonstrate that discriminative predictions improve by leveraging an extra time-to-event variable. Conclusions: Multiple time-to-event variables can be successfully captured within the harmonium paradigm.

We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. These bounds improve over the existing information-theoretic bounds, are applicable to a wider range of algorithms, and solve two key challenges: (a) they give meaningful results for deterministic algorithms and (b) they are significantly easier to estimate. We show experimentally that the proposed bounds closely follow the generalization gap in practical scenarios for deep learning.

Welcome to AI book reviews, a series of posts that explore the latest literature on artificial intelligence. Recent advances in deep learning have rekindled interest in the imminence of machines that can think and act like humans, or artificial general intelligence. By following the path of building bigger and better neural networks, the thinking goes, we will be able to get closer and closer to creating a digital version of the human brain. But this is a myth, argues computer scientist Erik Larson, and all evidence suggests that human and machine intelligence are radically different. Larson's new book, The Myth of Artificial Intelligence: Why Computers Can't Think the Way We Do, discusses how widely publicized misconceptions about intelligence and inference have led AI research down narrow paths that are limiting innovation and scientific discoveries.

Artificial intelligence (AI) will create new job opportunities, not destroy them. AI will displace some jobs but will create new ones. The main aim of this article is intended to focus the minds of our political and business leaders as they consider what strategies to pursue to grow the economy (GDP), business activity and stimulate job creation whilst also taking into account the growing challenges of the environment with climate change mitigation increasingly on the agenda. Let's start by reviewing the types of AI and where we are now. Narrow AI: the field of AI where the machine is designed to perform a single task and the machine gets very good at performing that particular task.

Having flexed its muscles in predicting kidney injury, toppling Go champions and solving 50-year-old science problems, artificial intelligence company DeepMind is now dipping its toes in weather forecasting. The company's latest tool is designed to predict oncoming precipitation through what's known as nowcasting, and the vast majority of meteorologists found it to be more accurate than current methods in early testing. The science of precipitation nowcasting focuses on predicting rain within the next one to two hours, and is of real importance in areas such as outdoor events, aviation and emergency planning. DeepMind set out to develop a machine-learning tool that can bring a new level of precision to these efforts, by making use of high-precision radar data that tracks precipitation every five minutes at a 1-km (0.62-mile) resolution. It did so by using a generative modeling approach, which analyzes the past 20 minutes of observed radar and then makes predictions for the upcoming 90 minutes.