To train parameters of our algorithm we need to perform gradient descent. When training neural network, it is important to initialize the parameters randomly rather then to all zeros. More about that you can see in this post.

Let's understand what machine learning is? In simple words, machine learning is all about making computers to perform intelligent tasks without explicitly coding. This is achieved by training the computer with lots and lots of data. For example, detecting whether a mail is a spam or not recognizing handwritten digit, fraud detection in transactions and many such applications. Now let's see what are the top five skills to get a machine learning job?

Welcome to the world of machine learning with scikit-learn. Machine learning can be overwhelming at times, and this is partly due to a large number of tools that are available on the market. This post will simplify this process of tool selection down to one -- scikit-learn. In this series, you will learn how to construct an end-to-end machine learning pipeline using some of the most popular algorithms that are widely used in industry and professional competitions, such as Kaggle. Now, let's begin this fun journey into the world of machine learning with scikit-learn!

Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking. We provide case studies to demonstrate that, qualitatively, image retrieval based on Graph-RISE effectively captures semantics and, compared to the state-of-the-art, differentiates nuances at levels that are closer to human-perception.

We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when the gradient has random errors in the form of additive white noise. With gradient errors, the function values of the iterates need not converge to the optimal value; hence, we define the robustness of an algorithm to noise as the asymptotic expected suboptimality of the iterate sequence to input noise power. For this robustness measure, we provide exact expressions for the quadratic case using tools from robust control theory and tight upper bounds for the smooth strongly convex case using Lyapunov functions certified through matrix inequalities. We use these characterizations within an optimization problem which selects parameters of each algorithm to achieve a particular trade-off between rate and robustness. Our results show that AG can achieve acceleration while being more robust to random gradient errors. This behavior is quite different than previously reported in the deterministic gradient noise setting. We also establish some connections between the robustness of an algorithm and how quickly it can converge back to the optimal solution if it is perturbed from the optimal point with deterministic noise. Our framework also leads to practical algorithms that can perform better than other state-of-the-art methods in the presence of random gradient noise.

Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to increase the receptive field, we propose a novel deep Hierarchical Graph Convolutional Network (H-GCN) for semi-supervised node classification. H-GCN first repeatedly aggregates structurally similar nodes to hyper-nodes and then refines the coarsened graph to the original to restore the representation for each node. Instead of merely aggregating one- or two-hop neighborhood information, the proposed coarsening procedure enlarges the receptive field for each original node, hence more global information can be learned. Comprehensive experiments conducted on public datasets demonstrate effectiveness of the proposed method over the state-of-art methods. Notably, our model gains substantial improvements when only very few labeled samples are provided.

Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoretical foundation of DNNs and promotes their usability in different areas of artificial intelligence. In this paper, we investigate the role of Rademacher complexity in improving generalization of DNNs and propose a novel regularizer rooted in Local Rademacher Complexity (LRC). While Rademacher complexity is well known as a distribution-free complexity measure of function class that help boost generalization of statistical learning methods, extensive study shows that LRC, its counterpart focusing on a restricted function class, leads to sharper convergence rates and potential better generalization given finite training sample. Our LRC based regularizer is developed by estimating the complexity of the function class centered at the minimizer of the empirical loss of DNNs. Experiments on various types of network architecture demonstrate the effectiveness of LRC regularization in improving generalization. Moreover, our method features the state-of-the-art result on the CIFAR-$10$ dataset with network architecture found by neural architecture search.

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning, this line of research is in its infancy, and how to design and optimize suitable loss functions to train deep neural networks for clustering is still an open question. Our contribution to this emerging field is a new deep clustering network that leverages the discriminative power of information-theoretic divergence measures, which have been shown to be effective in traditional clustering. We propose a novel loss function that incorporates geometric regularization constraints, thus avoiding degenerate structures of the resulting clustering partition. Experiments on synthetic benchmarks and real datasets show that the proposed network achieves competitive performance with respect to other state-of-the-art methods, scales well to large datasets, and does not require pre-training steps.

This work introduces the first simple and provably correct solution for recovering a low-rank matrix from phaseless (magnitude-only) linear projections of each of its columns. This problem finds important applications in phaseless dynamic imaging, e.g., Fourier ptychographic imaging of live biological specimens. We demonstrate the practical advantage of our proposed approach, AltMinLowRaP, over existing work via extensive simulation, and some real-data, experiments. Under a right incoherence (denseness of right singular vectors) assumption, our guarantee shows that, in the regime of small ranks, r, the sample complexity of AltMinLowRaP is much smaller than what standard phase retrieval methods need; and it is only $r^3$ times the order-optimal complexity for low-rank matrix recovery. We also provide a solution for a dynamic extension of the above problem. This allows the low-dimensional subspace from which each image/signal is generated to change with time in a piecewise constant fashion.