Quora recently announced the first public dataset that they ever released. It includes 404351 question pairs with a label column indicating if they are duplicate or not. In this post, I like to investigate this dataset and at least propose a baseline method with deep learning. Beside the proposed method, it includes some examples showing how to use Pandas, Gensim, Spacy and Keras. For the full code you check Github.

When I tell people that I work at an AI company, they often follow up with, "So, what kind of machine learning/deep learning do you do?" This isn't surprising, as most of the market attention (and hype) in and around AI has been centered around machine learning and its high-profile subset deep learning and around natural language processing with the rise of the chatbot and virtual assistants. But while machine learning is a core component of artificial intelligence, AI is, in fact, more than just ML. So, what does it really mean for an application to be "intelligent"? What does it take to create a system that is artificially intelligent?

Google on Wednesday shared some details regarding the performance of its custom-built Tensor Processing Unit (TPU) chip. Designed for machine learning and tailored for TensorFlow, Google's open-source machine learning framework, TPUs have been powering Google datacenters since 2015. This first generation of TPUs, Google noted, have targeted inference -- the use of an already trained model, as opposed to the training phase of a model. On production AI workloads that utilize neural network inference, the TPU is 15 times to 30 times faster than contemporary GPUs and CPUs, Google said. Additionally, the TPU is much more energy efficient, delivering a 30 times to 80 times improvement in TOPS/Watt measure (tera-operations [trillion or 1012 operations] of computation per Watt of energy consumed).

Hi i there My name is Bryan Downing. I am part of a company called QuantLabs.Net This is specifically a company with a high profile blog about technology, trading, financial, investment, quant, etc. It posts things on how to do job interviews with large companies like Morgan Stanley, Bloomberg, Citibank, and IBM. It also posts different unique tips and tricks on Java, C, or C programming. It posts about different techniques in learning about Matlab and building models or strategies.

Three-dimensional views of human stem cells derived from skin showing DNA (blue), the cell membrane (purple) and other structures in yellow. No two stem cells are identical, even if they are genetic clones. This stunning diversity is revealed today in an enormous publicly available online catalogue of 3D stem cell images. The visuals were produced using deep learning analyses and cell lines altered with the gene-editing tool CRISPR. And soon the portal will allow researchers to predict variations in cell layouts that may foreshadow cancer and other diseases.

The science of deep learning, a sub-discipline of artificial intelligence (AI), is only a recent development in the grand scheme of things, but during its short existence, it has been producing some impressive technological achievements. Advances in image recognition, language understanding, and translation have led to the development of virtual assistants, smart home speakers, and gains in cybersecurity, and they are leading the charge toward autonomous driving. Now, companies have found a way to use those AI smarts to fight cancer. Deep learning involves the construction of artificial neural networks, using software and complex algorithms to recreate the capacity of the human brain to learn. These learning computers have a particular knack for sifting through vast amounts of data and recognizing patterns, getting smarter as they go.

What is your stance on AI research given Canada's privileged position in the field? I've been personally fascinated by AI ever since high school when I read books like Roger Penrose's Emperor's New Mind and Douglas Hofstadter's The Mind's I. So it's really exciting for me to be able to encourage Canadian leadership in the field today. You see, strong public support for research programs and world class expertise at Canadian universities has helped propel Canada to a position as leader in artificial intelligence and deep learning research and use. Canadian talent and ideas are in high demand around the world--but activity needs to remain in Canada to harness the benefits from artificial intelligence.

A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simulate heredity and determine the architectures of offspring networks. In this study, we take a deeper look at the notion of synaptic cluster-driven evolution of deep neural networks which guides the evolution process towards the formation of a highly sparse set of synaptic clusters in offspring networks. Utilizing a synaptic cluster-driven genetic encoding, the probabilistic encoding of synaptic traits considers not only individual synaptic properties but also inter-synaptic relationships within a deep neural network. This process results in highly sparse offspring networks which are particularly tailored for parallel computational devices such as GPUs and deep neural network accelerator chips. Comprehensive experimental results using four well-known deep neural network architectures (LeNet-5, AlexNet, ResNet-56, and DetectNet) on two different tasks (object categorization and object detection) demonstrate the efficiency of the proposed method. Cluster-driven genetic encoding scheme synthesizes networks that can achieve state-of-the-art performance with significantly smaller number of synapses than that of the original ancestor network. ($\sim$125-fold decrease in synapses for MNIST). Furthermore, the improved cluster efficiency in the generated offspring networks ($\sim$9.71-fold decrease in clusters for MNIST and a $\sim$8.16-fold decrease in clusters for KITTI) is particularly useful for accelerated performance on parallel computing hardware architectures such as those in GPUs and deep neural network accelerator chips.

Why do large neural network generalize so well on complex tasks such as image classification or speech recognition? What exactly is the role regularization for them? These are arguably among the most important open questions in machine learning today. In a recent and thought provoking paper [C. Zhang et al.] several authors performed a number of numerical experiments that hint at the need for novel theoretical concepts to account for this phenomenon. The paper stirred quit a lot of excitement among the machine learning community but at the same time it created some confusion as discussions on OpenReview.net testifies. The aim of this pedagogical paper is to make this debate accessible to a wider audience of data scientists without advanced theoretical knowledge in statistical learning. The focus here is on explicit mathematical definitions and on a discussion of relevant concepts, not on proofs for which we provide references.

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it difficult to use them for adaptive stepsize selection and automatic stopping. We propose alternative "big batch" SGD schemes that adaptively grow the batch size over time to maintain a nearly constant signal-to-noise ratio in the gradient approximation. The resulting methods have similar convergence rates to classical SGD, and do not require convexity of the objective. The high fidelity gradients enable automated learning rate selection and do not require stepsize decay. Big batch methods are thus easily automated and can run with little or no oversight.