Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations (or ``chain-of-thought'' (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for symbolic programming. To make progress towards understanding in-context learning, we curate synthetic datasets containing equivalent (natural, symbolic) data pairs, where symbolic examples contain first-order logic rules and predicates from knowledge bases (KBs). Then we revisit neuro-symbolic approaches and use Language Models as Logic Programmer (LMLP) that learns from demonstrations containing logic rules and corresponding examples to iteratively reason over KBs, recovering Prolog's backward chaining algorithm. Comprehensive experiments are included to systematically compare LMLP with CoT in deductive reasoning settings, showing that LMLP enjoys more than 25% higher accuracy than CoT on length generalization benchmarks even with fewer parameters.

Quantum computers offer the potential of achieving significant speedup for certain computational problems. Yet, many existing quantum algorithms with notable asymptotic speedups require a degree of fault tolerance that is currently unavailable. The quantum algorithm for topological data analysis (TDA) by Lloyd et al. is believed to be one such algorithm. TDA is a powerful technique for extracting complex and valuable shape-related summaries of high-dimensional data. However, the computational demands of classical TDA algorithms are exorbitant, and become impractical for high-order characteristics. In this paper, we present NISQ-TDA, the first fully implemented end-to-end quantum machine learning algorithm needing only a short circuit-depth, that is applicable to non-handcrafted high-dimensional classical data, and with provable asymptotic speedup for certain classes of problems. The algorithm neither suffers from the data-loading problem nor does it need to store the input data on the quantum computer explicitly. Our approach includes three key innovations: an efficient realization of the full boundary operator; a quantum rejection sampling and projection approach to restrict a quantum state to the simplices of the desired order in the given complex; and a stochastic rank estimation method to estimate the topological features in the form of approximate Betti numbers. We present theoretical results that establish additive error guarantees, along with computational cost and circuit-depth complexities for normalized output estimates, up to the error tolerance. The algorithm was successfully executed on quantum computing devices, as well as on noisy quantum simulators, applied to small datasets. Preliminary empirical results suggest that the algorithm is robust to noise. Finally, we provide target depths and noise level estimates to realize near-term, non-fault-tolerant quantum advantage.

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the latent space, known as posterior collapse. To mitigate this, state-of-the-art models'weaken' the'powerful' decoder by applying uniformly random dropout to the decoder input. We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. We then propose an adversarial training strategy to achieve information-based stochastic dropout. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence modeling performance and the information captured in the latent space.

The robustness of machine learning algorithms to distributions shift is primarily discussed in the context of supervised learning (SL). As such, there is a lack of insight on the robustness of the representations learned from unsupervised methods, such as self-supervised learning (SSL) and auto-encoder based algorithms (AE), to distribution shift. We posit that the input-driven objectives of unsupervised algorithms lead to representations that are more robust to distribution shift than the target-driven objective of SL. We verify this by extensively evaluating the performance of SSL and AE on both synthetic and realistic distribution shift datasets. Following observations that the linear layer used for classification itself can be susceptible to spurious correlations, we evaluate the representations using a linear head trained on a small amount of out-of-distribution (OOD) data, to isolate the robustness of the learned representations from that of the linear head. We also develop "controllable" versions of existing realistic domain generalisation datasets with adjustable degrees of distribution shifts. This allows us to study the robustness of different learning algorithms under versatile yet realistic distribution shift conditions. Our experiments show that representations learned from unsupervised learning algorithms generalise better than SL under a wide variety of extreme as well as realistic distribution shifts.

So, here we are once more with a sense of nostalgia as one year comes to an end and another awaits to begin. But just as tech courses were in high demand in 2022, in 2023, technology courses will play an even bigger role in education and career opportunities. As technology is continuously evolving, there's always something new and exciting to pursue. As a matter of fact, you have to be constantly on the lookout for where technology is headed and stay relevant with new and cutting-edge skills. In other words, in the tech space, "you have to run, just to stand still".

Rose Nakasi and her colleagues have developed a machine-learning method to detect malaria parasites in blood samples. We spoke to Rose about the motivation for this project, the progress so far, and what they are planning next. The problem that we are trying to solve concerns the microscopy of malaria diagnosis. The motivation for this research is that malaria is one of the most highly endemic diseases in sub-Saharan Africa, Uganda included. The major problem is that the gold-standard confirmatory test for diagnosis is by use of a microscope, and in our setting, we have a shortage of skilled lab microscopists that are able to carry out the correct diagnosis of the disease.

The world is making rapid progress in the areas of Big Data, Artificial Intelligence and Machine Learning. These are the core drivers of what many analysts have come to refer to as the Fourth Industrial Revolution, epitomised by the increased whittling away of the boundaries that hitherto existed between the physical, digital and biological worlds. There is a clear imperative for pharmacists, pharmaceutical scientists and medical professionals in the field of research and development in developing countries like Nigeria, to increasingly tap into this world of Big Data, Artificial Intelligence and Machine Learning and partake of the revolution that is happening before our very eyes. And the reason is simple. Artificial Intelligence is helping to make pharmaceutical research and new drug discovery less expensive and definitely more productive. Researchers realise that in the time that it would have taken to test the efficacy of say a handful of chemical molecules manually, with AI, it is possible to test several hundreds of different chemical molecules.

Computer vision is a field of artificial intelligence that teaches computers to interpret and understand the visual world. Its applications are critical for the development of AI-powered technologies such as self-driving cars, autonomous drones, industrial robots, and augmented reality headsets, among numerous other technologies. Companies that are into the development of critical components of computer vision systems are in all rights computer vision companies. This includes computer vision chip makers and companies offering full computer vision solutions. The continuous increase in computer vision technologies also provides an excellent opportunity for investors to make fortunes by investing in recession-proof computer vision stocks.

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and LAION have propelled recent dramatic progress in AI. Large neural models trained on such datasets produce impressive results and top many of today's benchmarks. A notable omission within this family of large-scale datasets is 3D data. Despite considerable interest and potential applications in 3D vision, datasets of high-fidelity 3D models continue to be mid-sized with limited diversity of object categories. Addressing this gap, we present Objaverse 1.0, a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category. We demonstrate the large potential of Objaverse via four diverse applications: training generative 3D models, improving tail category segmentation on the LVIS benchmark, training open-vocabulary object-navigation models for Embodied AI, and creating a new benchmark for robustness analysis of vision models. Objaverse can open new directions for research and enable new applications across the field of AI.

Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing attention variants that improve the computational efficiency, but they have limited ability to effectively compute global information. In parallel to Transformer models, state space models (SSMs) are tailored for long sequences, but they are not flexible enough to capture complicated local information. We propose SPADE, short for $\underline{\textbf{S}}$tate s$\underline{\textbf{P}}$ace $\underline{\textbf{A}}$ugmente$\underline{\textbf{D}}$ Transform$\underline{\textbf{E}}$r. Specifically, we augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. The SSM augments global information, which complements the lack of long-range dependency issue in local attention methods. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method. To further demonstrate the scalability of SPADE, we pre-train large encoder-decoder models and present fine-tuning results on natural language understanding and natural language generation tasks.