It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training. This has been shown in a host of settings such as generic object classification and detection, semantic segmentation, and image retrieval. However, some issues have recently come to the fore that demonstrate some of the failure modes of self-supervised representations, such as performance on non-ImageNet-like data, or complex scenes. In this paper, we show that self-supervised representations based on the instance discrimination objective lead to better representations of objects that are more robust to changes in the viewpoint and perspective of the object. We perform experiments of modern self-supervised methods against multiple supervised baselines to demonstrate this, including approximating object viewpoint variation through homographies, and real-world tests based on several multi-view datasets. We find that self-supervised representations are more robust to object viewpoint and appear to encode more pertinent information about objects that facilitate the recognition of objects from novel views.

Non-local (NL) block is a popular module that demonstrates the capability to model global contexts. However, NL block generally has heavy computation and memory costs, so it is impractical to apply the block to high-resolution feature maps. In this paper, to investigate the efficacy of NL block, we empirically analyze if the magnitude and direction of input feature vectors properly affect the attention between vectors. The results show the inefficacy of softmax operation which is generally used to normalize the attention map of the NL block. Attention maps normalized with softmax operation highly rely upon magnitude of key vectors, and performance is degenerated if the magnitude information is removed. By replacing softmax operation with the scaling factor, we demonstrate improved performance on CIFAR-10, CIFAR-100, and Tiny-ImageNet. In Addition, our method shows robustness to embedding channel reduction and embedding weight initialization. Notably, our method makes multi-head attention employable without additional computational cost.

Ten years into the revival of deep networks and artificial intelligence, we propose a theoretical framework that sheds light on understanding deep networks within a bigger picture of Intelligence in general. We introduce two fundamental principles, Parsimony and Self-consistency, that address two fundamental questions regarding Intelligence: what to learn and how to learn, respectively. We believe the two principles are the cornerstones for the emergence of Intelligence, artificial or natural. While these two principles have rich classical roots, we argue that they can be stated anew in entirely measurable and computable ways. More specifically, the two principles lead to an effective and efficient computational framework, compressive closed-loop transcription, that unifies and explains the evolution of modern deep networks and many artificial intelligence practices. While we mainly use modeling of visual data as an example, we believe the two principles will unify understanding of broad families of autonomous intelligent systems and provide a framework for understanding the brain.

We present the corpus called HealthCall. This was recorded in real-life conditions in the call center of Malakoff Humanis. It includes two separate audio channels, the first one for the customer and the second one for the agent. Each conversation was anonymized respecting the General Data Protection Regulation. This corpus includes a transcription of the spoken conversations and was divided into two sets: Train and Devel sets. Two important customer relationship management tasks were assessed on the HealthCall corpus: Automatic prediction of type of user requests and complaints detection. For this purpose, we have investigated 14 feature sets: 6 linguistic feature sets, 6 audio feature sets and 2 vocal interaction feature sets. We have used Bidirectional Encoder Representation from Transformers models for the linguistic features, openSMILE and Wav2Vec 2.0 for the audio features. The vocal interaction feature sets were designed and developed from Turn Takings. The results show that the linguistic features always give the best results (91.2% for the Request task and 70.3% for the Complaint task). The Wav2Vec 2.0 features seem more suitable for these two tasks than the ComPaRe16 features. Vocal interaction features outperformed ComPaRe16 features on Complaint task with a 57% rate achieved with only six features.

While deep neural networks are capable of achieving state-of-the-art performance in various domains, their training typically requires iterating for many passes over the dataset. However, due to computational and memory constraints and potential privacy concerns, storing and accessing all the data is impractical in many real-world scenarios where the data arrives in a stream. In this paper, we investigate the problem of one-pass learning, in which a model is trained on sequentially arriving data without retraining on previous datapoints. Motivated by the increasing use of overparameterized models, we develop Orthogonal Recursive Fitting (ORFit), an algorithm for one-pass learning which seeks to perfectly fit every new datapoint while changing the parameters in a direction that causes the least change to the predictions on previous datapoints. By doing so, we bridge two seemingly distinct algorithms in adaptive filtering and machine learning, namely the recursive least-squares (RLS) algorithm and orthogonal gradient descent (OGD). Our algorithm uses the memory efficiently by exploiting the structure of the streaming data via an incremental principal component analysis (IPCA). Further, we show that, for overparameterized linear models, the parameter vector obtained by our algorithm is what stochastic gradient descent (SGD) would converge to in the standard multi-pass setting. Finally, we generalize the results to the nonlinear setting for highly overparameterized models, relevant for deep learning. Our experiments show the effectiveness of the proposed method compared to the baselines.

The MINSU(Mobile Inventory and Scanning Unit) algorithm uses the computational vision analysis method to record the residual quantity/fullness of the cabinet. To do so, it goes through a five-step method: object detection, foreground subtraction, K-means clustering, percentage estimation, and counting. The input image goes through the object detection method to analyze the specific position of the cabinets in terms of coordinates. After doing so, it goes through the foreground subtraction method to make the image more focus-able to the cabinet itself by removing the background (some manual work may have to be done such as selecting the parts that were not grab cut by the algorithm). In the K-means clustering method, the multi-colored image turns into a 3 colored monotonous image for quicker and more accurate analysis. At last, the image goes through percentage estimation and counting. In these two methods, the proportion that the material inside the cabinet is found in percentage which then is used to approximate the number of materials inside. Had this project been successful, the residual quantity management could solve the problem addressed earlier in the introduction.

Abstract--This paper proposes Federated Learning (FL) based smart healthcare system where Medical Centers (MCs) train the local model using the data collected from patients and send the model weights to the miners in a blockchain-based robust framework without sharing raw data, keeping privacy preservation into deliberation. We formulate an optimization problem by maximizing the utility and minimizing the loss function considering energy consumption and FL process delay of MCs for learning effective models on distributed healthcare data underlying a blockchain-based framework. We propose a solution in two stages-first, offer a stable matching-based association algorithm to maximize the utility of both miners and MCs and then solve loss minimization using Stochastic Gradient Descent (SGD) algorithm employing FL under Differential Privacy (DP) and blockchain technology. Moreover, we incorporate blockchain technology to provide tempered resistant and decentralized model weight sharing in the proposed FL-based framework. The effectiveness of the proposed model is shown through simulation on real-world healthcare data comparing other state-of-the-art techniques.

The important recent book by G. Schurz appreciates that the no-free-lunch theorems (NFL) have major implications for the problem of (meta) induction. Here I review the NFL theorems, emphasizing that they do not only concern the case where there is a uniform prior -- they prove that there are "as many priors" (loosely speaking) for which any induction algorithm $A$ out-generalizes some induction algorithm $B$ as vice-versa. Importantly though, in addition to the NFL theorems, there are many {free lunch} theorems. In particular, the NFL theorems can only be used to compare the {marginal} expected performance of an induction algorithm $A$ with the marginal expected performance of an induction algorithm $B$. There is a rich set of free lunches which instead concern the statistical correlations among the generalization errors of induction algorithms. As I describe, the meta-induction algorithms that Schurz advocate as a "solution to Hume's problem" are just an example of such a free lunch based on correlations among the generalization errors of induction algorithms. I end by pointing out that the prior that Schurz advocates, which is uniform over bit frequencies rather than bit patterns, is contradicted by thousands of experiments in statistical physics and by the great success of the maximum entropy procedure in inductive inference.

Missing values, widely called as \textit{sparsity} in literature, is a common characteristic of many real-world datasets. Many imputation methods have been proposed to address this problem of data incompleteness or sparsity. However, the accuracy of a data imputation method for a given feature or a set of features in a dataset is highly dependent on the distribution of the feature values and its correlation with other features. Another problem that plagues industry deployments of machine learning (ML) solutions is concept drift detection, which becomes more challenging in the presence of missing values. Although data imputation and concept drift detection have been studied extensively, little work has attempted a combined study of the two phenomena, i.e., concept drift detection in the presence of sparsity. In this work, we carry out a systematic study of the following: (i) different patterns of missing values, (ii) various statistical and ML based data imputation methods for different kinds of sparsity, (iii) several concept drift detection methods, (iv) practical analysis of the various drift detection metrics, (v) selecting the best concept drift detector given a dataset with missing values based on the different metrics. We first analyze it on synthetic data and publicly available datasets, and finally extend the findings to our deployed solution of automated change risk assessment system. One of the major findings from our empirical study is the absence of supremacy of any one concept drift detection method across all the relevant metrics. Therefore, we adopt a majority voting based ensemble of concept drift detectors for abrupt and gradual concept drifts. Our experiments show optimal or near optimal performance can be achieved for this ensemble method across all the metrics.

Inspired by the use of random projections in biological sensing systems, we present a new algorithm for processing data in classification problems. This is based on observations of the human brain and the fruit fly's olfactory system and involves randomly projecting data into a space of greatly increased dimension before applying a cap operation to truncate the smaller entries. This leads to a simple algorithm that is very computationally efficient and can be used to either give a sparse representation with minimal loss in classification accuracy or give improved robustness, in the sense that classification accuracy is improved when noise is added to the data. This is demonstrated with numerical experiments, which supplement theoretical results demonstrating that the resulting signal transform is continuous and invertible, in an appropriate sense.