Existing work on sign language translation - that is, translation from sign language videos into sentences in a written language - has focused mainly on (1) data collected in a controlled environment or (2) data in a specific domain, which limits the applicability to real-world settings. In this paper, we introduce OpenASL, a large-scale American Sign Language (ASL) - English dataset collected from online video sites (e.g., YouTube). OpenASL contains 288 hours of ASL videos in multiple domains from over 200 signers and is the largest publicly available ASL translation dataset to date. To tackle the challenges of sign language translation in realistic settings and without glosses, we propose a set of techniques including sign search as a pretext task for pre-training and fusion of mouthing and handshape features. The proposed techniques produce consistent and large improvements in translation quality, over baseline models based on prior work. Our data and code are publicly available at https://github.com/chevalierNoir/OpenASL

Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency when performing inference with deep learning workloads. Error backpropagation is presently regarded as the most effective method for training SNNs, but in a twist of irony, when training on modern graphics processing units (GPUs) this becomes more expensive than non-spiking networks. The emergence of Graphcore's Intelligence Processing Units (IPUs) balances the parallelized nature of deep learning workloads with the sequential, reusable, and sparsified nature of operations prevalent when training SNNs. IPUs adopt multi-instruction multi-data (MIMD) parallelism by running individual processing threads on smaller data blocks, which is a natural fit for the sequential, non-vectorized steps required to solve spiking neuron dynamical state equations. We present an IPU-optimized release of our custom SNN Python package, snnTorch, which exploits fine-grained parallelism by utilizing low-level, pre-compiled custom operations to accelerate irregular and sparse data access patterns that are characteristic of training SNN workloads. We provide a rigorous performance assessment across a suite of commonly used spiking neuron models, and propose methods to further reduce training run-time via half-precision training. By amortizing the cost of sequential processing into vectorizable population codes, we ultimately demonstrate the potential for integrating domain-specific accelerators with the next generation of neural networks.

In this paper, we present a novel and generic data-driven method to servo-control the 3-D shape of continuum and soft robots embedded with fiber Bragg grating (FBG) sensors. Developments of 3-D shape perception and control technologies are crucial for continuum robots to perform the tasks autonomously in surgical interventions. However, owing to the nonlinear properties of continuum robots, one main difficulty lies in the modeling of them, especially for soft robots with variable stiffness. To address this problem, we propose a versatile learning-based adaptive controller by leveraging FBG shape feedback that can online estimate the unknown model of continuum robot against unexpected disturbances and exhibit an adaptive behavior to the unmodeled system without priori data exploration. Based on a new composite adaptation algorithm, the asymptotic convergences of the closed-loop system with learning parameters have been proven by Lyapunov theory. To validate the proposed method, we present a comprehensive experimental study by using two continuum robots both integrated with multi-core FBGs, including a robotic-assisted colonoscope and multi-section extensible soft manipulators. The results demonstrate the feasibility, adaptability, and superiority of our controller in various unstructured environments as well as phantom experiments.

Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which leverages the use of a different learning rate for each layer of a neural network to create a data-free curriculum during the initial training epochs. More specifically, LeRaC assigns higher learning rates to neural layers closer to the input, gradually decreasing the learning rates as the layers are placed farther away from the input. The learning rates increase at various paces during the first training iterations, until they all reach the same value. From this point on, the neural model is trained as usual. This creates a model-level curriculum learning strategy that does not require sorting the examples by difficulty and is compatible with any neural network, generating higher performance levels regardless of the architecture. We conduct comprehensive experiments on eight datasets from the computer vision (CIFAR-10, CIFAR-100, Tiny ImageNet), language (BoolQ, QNLI, RTE) and audio (ESC-50, CREMA-D) domains, considering various convolutional (ResNet-18, Wide-ResNet-50, DenseNet-121), recurrent (LSTM) and transformer (CvT, BERT, SepTr) architectures, comparing our approach with the conventional training regime. Moreover, we also compare with Curriculum by Smoothing (CBS), a state-of-the-art data-free curriculum learning approach. Unlike CBS, our performance improvements over the standard training regime are consistent across all datasets and models. Furthermore, we significantly surpass CBS in terms of training time (there is no additional cost over the standard training regime for LeRaC).

"I felt there's a gap between what I learned in school, and what I actually do, and I also feel very insecure sometimes," she said. "I didn't know a lot of other data scientists who worked in the industry, so I wished I could have a community and talk to them." Essentially, said Liu, a data scientist takes something raw and translates it into something meaningful. The power of data science, she explained, is making sense of the past to make a recommendation for the future. "A data scientist is basically someone who solves a business problem with data," she explained.

We’re entering a “new era of science”--we finally have enough data and technology to truly enable better drugs for patients, says insitro CEO Daphne Koller.

"Can't live this lifeless life anymore. Screens, lectures, messages, mails, marks, deadlines, expectations, this room, that laptop, religion, restrictions, health, family, feelings, theories, equations, numbers…………and me, reasons are many. These were the last words of a young student from a premier institution in India before he took his life. He was a young man in his prime who should have been happy and enjoying life. Was this a one-off incident?

Earlier this week, I wrote about the history of progressive math education, the culture wars it has inspired over the past hundred years, and the controversy over the California Math Framework. Today, I want to start with a much broader question: What do we really know about how to teach math to children? The answer is not all that much--and what little we do know is highly contested. An American math education usually proceeds in a linear fashion, with the idea that one subject prepares you for the next. Take, for example, the typical path through mathematics for a relatively advanced student.

"Waiting in front of the lecture hall for my next class to start, and beside me two students are discussing which AI program works best for writing their essays. Is this what I'm marking? The tweet by historian Carla Ionescu late last month captures growing unease about what artificial intelligence portends for traditional university assessment. "Tell me we're not there yet." But AI has been banging on the university's gate for some time now. In 2012, computer theorist Ben Goertzel proposed what he called the "robot university student test", arguing that an AI capable of obtaining a degree in a same ways as a human should be considered conscious. Goertzel's idea – an alternative to the more famous "Turing test" – might have remained a thought experiment were it not for the successes of AIs employing natural language processing (NLP): most famously, GPT-3, the language model created by the OpenAi research laboratory. Two years ago, computer scientist Nassim Dehouche published a piece demonstrating that GPT-3 could produce credible academic writing undetectable by the usual anti-plagiarism software. "[I] found the output," Dehouche told Guardian Australia, "to be indistinguishable from an excellent undergraduate essay, both in terms of soundness and originality.

AI has evolved into a powerful tool in recent years, allowing machines to think and act like humans. Furthermore, it has attracted the attention of tech companies all over the world and is regarded as the next significant technological shift following the evolution of mobile and cloud platforms. Some even refer to it as the "fourth industrial revolution.". Businesses that use AI and related technologies such as machine learning and deep learning to uncover new business insights. Artificial intelligence is a branch of computer science dealing with the simulation of intelligent behavior in computers.