BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization. However, our understanding of the inner workings of BC is still quite limited. We attempt to close this gap in four different aspects: (a) we show that existing quantization algorithms, including post-training quantization, are surprisingly similar to each other; (b) we argue for proximal maps as a natural family of quantizers that is both easy to design and analyze; (c) we refine the observation that BC is a special case of dual averaging, which itself is a special case of the generalized conditional gradient algorithm; (d) consequently, we propose ProxConnect (PC) as a generalization of BC and we prove its convergence properties by exploiting the established connections. We conduct experiments on CIFAR-10 and ImageNet, and verify that PC achieves competitive performance.

Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we can use deep learning to directly predict these parameters by exploiting the past knowledge of training other networks. We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet. By leveraging advances in graph neural networks, we propose a hypernetwork that can predict performant parameters in a single forward pass taking a fraction of a second, even on a CPU. The proposed model achieves surprisingly good performance on unseen and diverse networks. For example, it is able to predict all 24 million parameters of a ResNet-50 achieving a 60% accuracy on CIFAR-10. On ImageNet, top-5 accuracy of some of our networks approaches 50%. Our task along with the model and results can potentially lead to a new, more computationally efficient paradigm of training networks. Our model also learns a strong representation of neural architectures enabling their analysis.

Model efficiency is a critical aspect of developing and deploying machine learning models. Inference time and latency directly affect the user experience, and some applications have hard requirements. In addition to inference costs, model training also have direct financial and environmental impacts. Although there are numerous well-established metrics (cost indicators) for measuring model efficiency, researchers and practitioners often assume that these metrics are correlated with each other and report only few of them. In this paper, we thoroughly discuss common cost indicators, their advantages and disadvantages, and how they can contradict each other. We demonstrate how incomplete reporting of cost indicators can lead to partial conclusions and a blurred or incomplete picture of the practical considerations of different models. We further present suggestions to improve reporting of efficiency metrics.

Despite several attempts, the fundamental mechanisms behind the success of deep neural networks still remain elusive. To this end, we introduce a novel analytic framework to unveil hidden convexity in training deep neural networks. We consider a parallel architecture with multiple ReLU sub-networks, which includes many standard deep architectures and ResNets as its special cases. We then show that the training problem with path regularization can be cast as a single convex optimization problem in a high-dimensional space. We further prove that the equivalent convex program is regularized via a group sparsity inducing norm. Thus, a path regularized parallel architecture with ReLU sub-networks can be viewed as a parsimonious feature selection method in high-dimensions. More importantly, we show that the computational complexity required to globally optimize the equivalent convex problem is polynomial-time with respect to the number of data samples and feature dimension. Therefore, we prove exact polynomial-time trainability for path regularized deep ReLU networks with global optimality guarantees. We also provide several numerical experiments corroborating our theory.

Equivariance has emerged as a desirable property of representations of objects subject to identity-preserving transformations that constitute a group, such as translations and rotations. However, the expressivity of a representation constrained by group equivariance is still not fully understood. We address this gap by providing a generalization of Cover's Function Counting Theorem that quantifies the number of linearly separable and group-invariant binary dichotomies that can be assigned to equivariant representations of objects. We find that the fraction of separable dichotomies is determined by the dimension of the space that is fixed by the group action. We show how this relation extends to operations such as convolutions, element-wise nonlinearities, and global and local pooling. While other operations do not change the fraction of separable dichotomies, local pooling decreases the fraction, despite being a highly nonlinear operation. Finally, we test our theory on intermediate representations of randomly initialized and fully trained convolutional neural networks and find perfect agreement.

Deep learning is a form of machine learning which allows a computer to learn from experience and understand things from a hierarchy of concepts where each concept being defined from a simpler one. This approach avoids the need for humans to specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them on top of each other through a deep setup with many layers. The first thing you need to learn when it comes to learning deep learning is the applied math which is the fundamental building block of deep learning. Linear algebra is a branch of mathematics that is widely used throughout engineering.

I work in Machine Learning. To readers/viewers of my work, this won't come as a surprise. To people who don't know me as well, feel free to check out my LinkedIn/articles/videos for a better understanding of my skills/experience. My specialty is in statistical analysis. I've had experience working in Road Safety, Health System Analysis, Big Data Analysis for a Bank, disease detection, biometric recreation, and currently work in Supply Chain Analysis.

Jack Clark, OpenAI's policy director, calls this trend of copying GPT-3, "model diffusion." Yet, among all the copies, Wu Dao 2.0 holds the record of being the largest of all with a striking 1.75 trillion parameters (10x GPT-3). Coco Feng reported for South China Morning Post that Wu Dao 2.0 was trained on 4.9TB of high-quality text and image data, which makes GPT-3's training dataset (570GB) pale in comparison. Yet, it's worth noting OpenAI researchers curated 45TB of data to extract clean those 570GB. It can learn from text and images and tackle tasks that include both types of data (something GPT-3 can't do).

It is a broad branch that includes machine learning and deep learning.

Artificial intelligence (AI) has become a part of everyday modern life and continues to generate excitement. In this article, we will take a look at how biotechs are advancing into AI-facilitated early drug design, its real-world outcomes so far, and whether it is living up to its potential in the life science industry. AI enables computers and machines to learn from past behavior and mistakes, much like humans can. From search algorithms to self-driving cars and Siri, it is cemented in our daily lives. In complex drug discovery, AI has the potential to make processes faster and more cost-effective, with the hope of reducing the time a new drug needs to reach the patient.