Using logical clauses to represent patterns, Tsetlin machines (TMs) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. A team of Tsetlin automata (TAs) composes each clause, thus driving the entire learning process. These are rewarded/penalized according to three local rules that optimize global behaviour. Each clause votes for or against a particular class, with classification resolved using a majority vote. In the parallel and asynchronous architecture that we propose here, every clause runs in its own thread for massive parallelism. For each training example, we keep track of the class votes obtained from the clauses in local voting tallies. The local voting tallies allow us to detach the processing of each clause from the rest of the clauses, supporting decentralized learning. Thus, rather than processing training examples one-by-one as in the original TM, the clauses access the training examples simultaneously, updating themselves and the local voting tallies in parallel. There is no synchronization among the clause threads, apart from atomic adds to the local voting tallies. Operating asynchronously, each team of TA will most of the time operate on partially calculated or outdated voting tallies. However, across diverse learning tasks, it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy. Further, we show that the approach provides up to 50 times faster learning. Finally, learning time is almost constant for reasonable clause amounts. For sufficiently large clause numbers, computation time increases approximately proportionally. Our parallel and asynchronous architecture thus allows processing of more massive datasets and operating with more clauses for higher accuracy.

Graph classification is a widely studied problem and has broad applications. In many real-world problems, the number of labeled graphs available for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose two approaches based on contrastive self-supervised learning (CSSL) to alleviate overfitting. In the first approach, we use CSSL to pretrain graph encoders on widely-available unlabeled graphs without relying on human-provided labels, then finetune the pretrained encoders on labeled graphs. In the second approach, we develop a regularizer based on CSSL, and solve the supervised classification task and the unsupervised CSSL task simultaneously. To perform CSSL on graphs, given a collection of original graphs, we perform data augmentation to create augmented graphs out of the original graphs. An augmented graph is created by consecutively applying a sequence of graph alteration operations. A contrastive loss is defined to learn graph encoders by judging whether two augmented graphs are from the same original graph. Experiments on various graph classification datasets demonstrate the effectiveness of our proposed methods.

This paper is concerned with learners who aim to learn patterns in infinite binary sequences: shown longer and longer initial segments of a binary sequence, they either attempt to predict whether the next bit will be a 0 or will be a 1 or they issue forecast probabilities for these events. Several variants of this problem are considered. In each case, a no-free-lunch result of the following form is established: the problem of learning is a formidably difficult one, in that no matter what method is pursued, failure is incomparably more common that success; and difficult choices must be faced in choosing a method of learning, since no approach dominates all others in its range of success. In the simplest case, the comparison of the set of situations in which a method fails and the set of situations in which it succeeds is a matter of cardinality (countable vs. uncountable); in other cases, it is a topological matter (meagre vs. co-meagre) or a hybrid computational-topological matter (effectively meagre vs. effectively co-meagre).

In this paper, we propose a novel method for video moment retrieval (VMR) that achieves state of the arts (SOTA) performance on R@1 metrics and surpassing the SOTA on the high IoU metric (R@1, IoU=0.7). First, we propose to use a multi-head self-attention mechanism, and further a cross-attention scheme to capture video/query interaction and long-range query dependencies from video context. The attention-based methods can develop frame-to-query interaction and query-to-frame interaction at arbitrary positions and the multi-head setting ensures the sufficient understanding of complicated dependencies. Our model has a simple architecture, which enables faster training and inference while maintaining . Second, We also propose to use multiple task training objective consists of moment segmentation task, start/end distribution prediction and start/end location regression task. We have verified that start/end prediction are noisy due to annotator disagreement and joint training with moment segmentation task can provide richer information since frames inside the target clip are also utilized as positive training examples. Third, we propose to use an early fusion approach, which achieves better performance at the cost of inference time. However, the inference time will not be a problem for our model since our model has a simple architecture which enables efficient training and inference.

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches $74.3\%$ top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and $79.6\%$ with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks. Our implementation and pretrained models are given on GitHub.

When it comes to machine learning classification tasks, the more data available to train algorithms, the better. In supervised learning, this data must be labeled with respect to the target class -- otherwise, these algorithms wouldn't be able to learn the relationships between the independent and target variables. So, what if we only have enough time and money to label some of a large data set, and choose to leave the rest unlabeled? Can this unlabeled data somehow be used in a classification algorithm? This is where semi-supervised learning comes in.

Limited power and computational resources, absence of high-end sensor equipment and GPS-denied environments are challenges faced by autonomous micro areal vehicles (MAVs). We address these challenges in the context of autonomous navigation and landing of MAVs in indoor environments and propose a vision-based control approach using Supervised Learning. To achieve this, we collected data samples in a simulation environment which were labelled according to the optimal control command determined by a path planning algorithm. Based on these data samples, we trained a Convolutional Neural Network (CNN) that maps low resolution image and sensor input to high-level control commands. We have observed promising results in both obstructed and non-obstructed simulation environments, showing that our model is capable of successfully navigating a MAV towards a landing platform. Our approach requires shorter training times than similar Reinforcement Learning approaches and can potentially overcome the limitations of manual data collection faced by comparable Supervised Learning approaches.

The first way we can characterize a contrastive self-supervised learning approach is by defining a data augmentation pipeline. A data augmentation pipeline A(x) applies a sequence of stochastic transformations to the same input. In deep learning, a data augmentation aims to build representations that are invariant to noise in the raw input. For example, the network should recognize the above pig as a pig even if it's rotated, or if the colors are gone or even if the pixels are "jittered" around. In contrastive learning, the data augmentation pipeline has a secondary goal which is to generate the anchor, positive and negative examples that will be fed to the encoder and will be used for extracting representations. CPC introduced a pipeline that applies transforms like color jitter, random greyscale, random flip, etc… but it also introduced a special transform that splits an image into overlaying sub patches.

We propose a new active learning (AL) framework, Active Learning++, which can utilize an annotator's labels as well as its rationale. Annotators can provide their rationale for choosing a label by ranking input features based on their importance for a given query. To incorporate this additional input, we modified the disagreement measure for a bagging-based Query by Committee (QBC) sampling strategy. Instead of weighing all committee models equally to select the next instance, we assign higher weight to the committee model with higher agreement with the annotator's ranking. Specifically, we generated a feature importance-based local explanation for each committee model. The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model. This approach is applicable to any kind of ML model using model-agnostic techniques to generate local explanation such as LIME. With a simulation study, we show that our framework significantly outperforms a QBC based vanilla AL framework.

Recent learning techniques for the representation of code depend mostly on human-annotated (labeled) data. In this work, we are proposing Corder, a self-supervised learning system that can learn to represent code without having to label data. The key innovation is that we train the source code model by asking it to recognize similar and dissimilar code snippets through a contrastive learning paradigm. We use a set of semantic-preserving transformation operators to generate snippets that are syntactically diverse but semantically equivalent. The contrastive learning objective, at the same time, maximizes agreement between different views of the same snippets and minimizes agreement between transformed views of different snippets. We train different instances of Corder on 3 neural network encoders, which are Tree-based CNN, ASTNN, and Code2vec over 2.5 million unannotated Java methods mined from GitHub. Our result shows that the Corder pre-training improves code classification and method name prediction with large margins. Furthermore, the code vectors generated by Corder are adapted to code clustering which has been shown to significantly beat the other baselines.