Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for "general continual learning". Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings. Continual learning (CL) refers to the ability of a learning agent to continuously interact with a dynamic environment and process a stream of information to acquire new knowledge while consolidating and retaining previously obtained knowledge (Parisi et al., 2019). This ability to continuously learn from a changing environment is a hallmark of intelligence and a critical missing component in our quest towards making our models truly intelligent. The major challenge towards enabling CL in deep neural networks (DNNs) is that the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting whereby the performance of the model on previously learned tasks drops drastically as it learns new tasks (McCloskey & Cohen, 1989). Several approaches have been proposed to address the issue of catastrophic forgetting in CL. Amongst these, rehearsal-based methods have proven to be more effective in challenging CL tasks (Farquhar & Gal, 2018). However, an optimal approach for replaying memory samples and constraining the model update to efficiently consolidate knowledge remains an open question.

Session-based recommendations (SBRs) recommend the next item for an anonymous user by modeling the dependencies between items in a session. Benefiting from the superiority of graph neural networks (GNN) in learning complex dependencies, GNN-based SBRs have become the main stream of SBRs in recent years. Most GNN-based SBRs are based on a strong assumption of adjacent dependency, which means any two adjacent items in a session are necessarily dependent here. However, based on our observation, the adjacency does not necessarily indicate dependency due to the uncertainty and complexity of user behaviours. Therefore, the aforementioned assumption does not always hold in the real-world cases and thus easily leads to two deficiencies: (1) the introduction of false dependencies between items which are adjacent in a session but are not really dependent, and (2) the missing of true dependencies between items which are not adjacent but are actually dependent. Such deficiencies significantly downgrade accurate dependency learning and thus reduce the recommendation performance. Aiming to address these deficiencies, we propose a novel review-refined inter-item graph neural network (RI-GNN), which utilizes the topic information extracted from items' reviews to refine dependencies between items. Experiments on two public real-world datasets demonstrate that RI-GNN outperforms the state-of-the-art methods.

Abstract--Random forests are considered one of the best out-of-the-box classification and regression algorithms due to their high level of predictive performance with relatively little tuning. Pairwise proximities can be computed from a trained random forest which measure the similarity between data points relative to the supervised task. Random forest proximities have been used in many applications including the identification of variable importance, data imputation, outlier detection, and data visualization. However, existing definitions of random forest proximities do not accurately reflect the data geometry learned by the random forest. In this paper, we introduce a novel definition of random forest proximities called Random Forest-Geometry-and Accuracy-Preserving proximities (RF-GAP). We prove that the proximity-weighted sum (regression) or majority vote (classification) using RF-GAP exactly match the out-of-bag random forest prediction, thus capturing the data geometry learned by the random forest. We empirically show that this improved geometric representation outperforms traditional random forest proximities in tasks such as data imputation and provides outlier detection and visualization results consistent with the learned data geometry. ANDOM forests [1] are well-known, powerful predictors comprised of an ensemble of binary recursive was first defined by Leo Breiman as the proportion of decision trees. Random forests are easily adapted for both trees in which the observations reside in the same terminal classification and regression, are trivially parallelizable, can node [16].

In November, the Internal Revenue Service launched an online security system that uses face recognition to confirm a person's identity. Public attention to the project last week triggered an outcry. The ACLU called the project "deeply troubling," saying face recognition "has been shown to be less accurate for people of color." Some IRS functions, like scheduling payments--but not filing taxes--now require first-time users to verify their identity with Virginia startup ID.me, which also works with 27 state employment agencies and the Veterans Administration. The process involves photographing a government-issued ID and uploading a video selfie so algorithms can match face and document.

In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that encompasses several subtasks such as slot tagging, coreference resolution, resolving plural mentions and entity linking. We approach this problem as an end-to-end modeling task where the conversational context is represented by an entity repository containing the entity references mentioned so far, their properties and the relationships between them. The repository is updated turn-by-turn, thus making training and inference computationally efficient even for long conversations. This paper lays the groundwork for an investigation of this framework in two ways. First, we release Contrack, a large scale human-human conversation corpus for context tracking with people and location annotations. It contains over 7000 conversations with an average of 11.8 turns, 5.8 entities and 15.2 references per conversation. Second, we open-source a neural network architecture for context tracking. Finally we compare this network to state-of-the-art approaches for the subtasks it subsumes and report results on the involved tradeoffs.

Breast cancer is in the most common malignant tumor in women. It accounted for 30% of new malignant tumor cases. Although the incidence of breast cancer remains high around the world, the mortality rate has been continuously reduced. This is mainly due to recent developments in molecular biology technology and improved level of comprehensive diagnosis and standard treatment. Early detection by mammography is an integral part of that. The most common breast abnormalities that may indicate breast cancer are masses and calcifications. Previous detection approaches usually obtain relatively high sensitivity but unsatisfactory specificity. We will investigate an approach that applies the discrete wavelet transform and Fourier transform to parse the images and extracts statistical features that characterize an image's content, such as the mean intensity and the skewness of the intensity. A naive Bayesian classifier uses these features to classify the images. We expect to achieve an optimal high specificity.

This paper tackles the problem of missing data imputation for noisy and non-Gaussian data. A classical imputation method, the Expectation Maximization (EM) algorithm for Gaussian mixture models, has shown interesting properties when compared to other popular approaches such as those based on k-nearest neighbors or on multiple imputations by chained equations. However, Gaussian mixture models are known to be not robust to heterogeneous data, which can lead to poor estimation performance when the data is contaminated by outliers or come from a non-Gaussian distributions. To overcome this issue, a new expectation maximization algorithm is investigated for mixtures of elliptical distributions with the nice property of handling potential missing data. The complete-data likelihood associated with mixtures of elliptical distributions is well adapted to the EM framework thanks to its conditional distribution, which is shown to be a Student distribution. Experimental results on synthetic data demonstrate that the proposed algorithm is robust to outliers and can be used with non-Gaussian data. Furthermore, experiments conducted on real-world datasets show that this algorithm is very competitive when compared to other classical imputation methods.

Collaborative filtering is the de facto standard for analyzing users' activities and building recommendation systems for items. In this work we develop Sliced Anti-symmetric Decomposition (SAD), a new model for collaborative filtering based on implicit feedback. In contrast to traditional techniques where a latent representation of users (user vectors) and items (item vectors) are estimated, SAD introduces one additional latent vector to each item, using a novel three-way tensor view of user-item interactions. This new vector extends user-item preferences calculated by standard dot products to general inner products, producing interactions between items when evaluating their relative preferences. SAD reduces to state-of-the-art (SOTA) collaborative filtering models when the vector collapses to one, while in this paper we allow its value to be estimated from data. The proposed SAD model is simple, resulting in an efficient group stochastic gradient descent (SGD) algorithm. We demonstrate the efficiency of SAD in both simulated and real world datasets containing over 1M user-item interactions. By comparing SAD with seven alternative SOTA collaborative filtering models, we show that SAD is able to more consistently estimate personalized preferences.

This post was cowritten by Ziv Pollak, Machine Learning Team Lead, and Sarvi Loloei, Machine Learning Engineer at Clearly. The content and opinions in this post are those of the third-party authors and AWS is not responsible for the content or accuracy of this post. A pioneer in online shopping, Clearly launched their first site in 2000. Since then, we've grown to become one of the biggest online eyewear retailers in the world, providing customers across Canada, the US, Australia, and New Zealand with glasses, sunglasses, contact lenses, and other eye health products. Through its mission to eliminate poor vision, Clearly strives to make eyewear affordable and accessible for everyone.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. The second most populous country in the world, India has enjoyed steady economic growth and has achieved self-sufficiency in grain production in recent years.