In an endeavour to upskill the youth and promote e-learning during the COVID-19 lockdown, IIT Roorkee had launched an Advanced Certification Course on Deep Learning at Cloudxlab.com. It is an advanced course on deep learning and would cover cutting edge techniques applicable to audio processing, image processing, video processing, self-driving cars etc. This came in the wake of the current economic crisis which underscores the significance of technical skills to tackle the global slowdown. Further to the launch IIT Roorkee and CloudxLab will conduct a webinar on careers in AI and machine learning. The webinar will include faculty members from IIT Roorkee as well as members of the industry.

The number of parameters of the conv2D layer corresponds to the weight matrix W of 5 5 and a b bias for each of the filters is 832 parameters (32 (25 1)). Max-pooling does not require parameters since it is a mathematical operation to find the maximum. And in order to build a "deep" neural network, we can stack several layers like the one built in the previous section. To show the reader how to do it in our example, we will create a second group of layers that will have 64 filters with a 5 5 window in the convolutional layer and a 2 2 window in the pooling layer.

Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model sizes, thereby bringing a series of deployment challenges. Although the state-of-the-art tensor decomposition approaches can provide good model compression performance, these existing methods are still suffering some inherent limitations, such as restricted representation capability and insufficient model complexity reduction. To overcome these limitations, in this paper we propose to develop compact RNN models using Hierarchical Tucker (HT) decomposition. HT decomposition brings strong hierarchical structure to the decomposed RNN models, which is very useful and important for enhancing the representation capability. Meanwhile, HT decomposition provides higher storage and computational cost reduction than the existing tensor decomposition approaches for RNN compression. Our experimental results show that, compared with the state-of-the-art compressed RNN models, such as TT-LSTM, TR-LSTM and BT-LSTM, our proposed HT-based LSTM (HT-LSTM), consistently achieves simultaneous and significant increases in both compression ratio and test accuracy on different datasets.

In order to extract knowledge from the large data collected by edge devices, traditional cloud based approach that requires data upload may not be feasible due to communication bandwidth limitation as well as privacy and security concerns of end users. To address these challenges, a novel privacy preserving edge computing framework is proposed in this paper for image classification. Specifically, autoencoder will be trained unsupervised at each edge device individually, then the obtained latent vectors will be transmitted to the edge server for the training of a classifier. This framework would reduce the communications overhead and protect the data of the end users. Comparing to federated learning, the training of the classifier in the proposed framework does not subject to the constraints of the edge devices, and the autoencoder can be trained independently at each edge device without any server involvement. Furthermore, the privacy of the end users' data is protected by transmitting latent vectors without additional cost of encryption. Experimental results provide insights on the image classification performance vs. various design parameters such as the data compression ratio of the autoencoder and the model complexity.

Reinforcement learning augmented by the representational power of deep neural networks, has shown promising results on high-dimensional problems, such as game playing and robotic control. However, the sequential nature of these problems poses a fundamental challenge for computational efficiency. Recently, alternative approaches such as evolutionary strategies and deep neuroevolution demonstrated competitive results with faster training time on distributed CPU cores. Here, we report record training times (running at about 1 million frames per second) for Atari 2600 games using deep neuroevolution implemented on distributed FPGAs. Combined hardware implementation of the game console, image pre-processing and the neural network in an optimized pipeline, multiplied with the system level parallelism enabled the acceleration. These results are the first application demonstration on the IBM Neural Computer, which is a custom designed system that consists of 432 Xilinx FPGAs interconnected in a 3D mesh network topology. In addition to high performance, experiments also showed improvement in accuracy for all games compared to the CPU-implementation of the same algorithm.

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.

As the advancement of deep learning (DL), the Internet of Things and cloud computing techniques for biomedical and healthcare problems, mobile healthcare systems have received unprecedented attention. Since DL techniques usually require enormous amount of computation, most of them cannot be directly deployed on the resource-constrained mobile and IoT devices. Hence, most of the mobile healthcare systems leverage the cloud computing infrastructure, where the data collected by the mobile and IoT devices would be transmitted to the cloud computing platforms for analysis. However, in the contested environments, relying on the cloud might not be practical at all times. For instance, the satellite communication might be denied or disrupted. We propose SAIA, a Split Artificial Intelligence Architecture for mobile healthcare systems. Unlike traditional approaches for artificial intelligence (AI) which solely exploits the computational power of the cloud server, SAIA could not only relies on the cloud computing infrastructure while the wireless communication is available, but also utilizes the lightweight AI solutions that work locally on the client side, hence, it can work even when the communication is impeded. In SAIA, we propose a meta-information based decision unit, that could tune whether a sample captured by the client should be operated by the embedded AI (i.e., keeping on the client) or the networked AI (i.e., sending to the server), under different conditions. In our experimental evaluation, extensive experiments have been conducted on two popular healthcare datasets. Our results show that SAIA consistently outperforms its baselines in terms of both effectiveness and efficiency.

Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e.g., African American Vernacular English, Colloquial Singapore English, etc.). We perturb the inflectional morphology of words to craft plausible and semantically similar adversarial examples that expose these biases in popular NLP models, e.g., BERT and Transformer, and show that adversarially fine-tuning them for a single epoch significantly improves robustness without sacrificing performance on clean data.

In a preprint paper, researchers at Alphabet's DeepMind and the University of California, Berkeley propose a framework for comparing the ways children and AI learn about the world. The work, which was motivated by research suggesting children's learning supports behaviors later in life, could help close the gap between AI and humans when it comes to acquiring new abilities. For instance, it might lead to robots that can pick and pack millions of different kinds of products while avoiding various obstacles. Exploration is a key feature of human behavior, and recent evidence suggests children explore their surroundings more often than adults. This is thought to translate to more learning that enables powerful, abstract task generalization -- a type of generalization AI agents could tangibly benefit from.

If you have to write an artificial intelligence (AI) or machine learning (ML) job description, it can be difficult to convey precisely what kind of new employee you want to hire. Doing so requires using the right language, plus understanding what type of role is most appropriate for what you want to achieve. To guide you through the challenging process of recruiting top AI talent, we'll start by looking at the differences between different AI & ML roles. Then, we'll discuss who should be your first hires depending on the approach you choose for your ML projects. We also recommend you make sure that you don't do these seven things to scare off the AI talent you're trying to hire.