Vanishing Gradient Problem occurs when we try to train a Neural Network model using Gradient based optimization techniques. Vanishing Gradient Problem was actually a major problem 10 years back to train a Deep neural Network Model due to the long training process and the degraded accuracy of the Model. What happens is that as we keep on adding more and more Hidden layers in The model, the learning speed of the next hidden layers in the model keep on getting faster and faster. Generally, adding more hidden layers tends to make the network able to learn more complex arbitrary functions, and thus do a better job in predicting future outcomes. This is where Deep Learning is making a big difference due to the thousands and millions of hidden layers it has, we can now make sense of highly complicated data such as images, speeches, videos etc and do Speech Recognition and Image Classification, Image Captioning etc. Now when we do Back-propagation i.e moving backward in the Network and calculating gradients of loss(Error) with respect to the weights, the gradients tends to get smaller and smaller as we keep on moving backward in the Network.

Data Scientist are changing the world but what do they really do? Basically a Data Scientist's job is to find correlation in data that might be able to predict outcomes. Most of the time their job is spent data cleansing and building models using their heavy math skills. The development and architecture cluster management is ran by the Data Engineer. If you like math and love data then Data Scientist might be the right career path for you.

Learn how to build and train a deep learning network to recognize numbers (MNIST),how to convert it in the CoreML format to then deploy it on your iPhoneX and make it recognize numbers in realtime! This is the third part of our deep learning on mobile phones series. In part one I have shown you the two main tricks on how to use convolutions and pooling to train deep learning networks. In part two I have shown you how to train existing deep learning networks like resnet50 to detect new objects. In part three I will now show you how to train a deep learning network, how to convert it in the CoreML format and then deploy it on your mobile phone!

Deep learning is a technology with a lot of promise: helping computers "see" the world, understand speech, and make sense of language. But away from the headlines about computers challenging humans at everything from spotting faces in a crowd to transcribing speech -- real-world performance has been more mixed. One deep-learning technology whose real-world results have often disappointed has been facial-recognition. In the UK, police in Cardiff and London used facial-recognition systems on multiple occasions in 2017 to flag persons of interest captured on video at major events. Unfortunately, more than 90% of people picked out by these systems were false matches.

There is not a huge difference in the RMSE value, but a plot for the predicted and actual values should provide a more clear understanding. The RMSE value is almost similar to the linear regression model and the plot shows the same pattern. Like linear regression, kNN also identified a drop in January 2018 since that has been the pattern for the past years. We can safely say that regression algorithms have not performed well on this dataset. Let's go ahead and look at some time series forecasting techniques to find out how they perform when faced with this stock prices prediction challenge. ARIMA is a very popular statistical method for time series forecasting. ARIMA models take into account the past values to predict the future values.

When working in healthcare, a lot of the relevant information for making accurate predictions and recommendations is only available in free-text clinical notes. Much of this data is trapped in free-text documents in unstructured form. This data is needed in order to make healthcare decisions. Hence, it is important to be able to extract data in the best possible way such that the information obtained can be analyzed and used. State-of-the-art NLP algorithms can extract clinical data from text using deep learning techniques such as healthcare-specific word embeddings, named entity recognition models, and entity resolution models.

These takeaways and many other fascinating insides are taken from the McKinsey Global Institute Discussion Paper "Notes from the AI frontier: Applications and Value of Deep Learning" The discussion paper draws on McKinsey Global Institute research and the firm's applied experience with the artificial intelligence of McKinsey Analytics, assessing the practical applications and the economic potential of advanced AI techniques. The discussion paper's findings are based on intensive McKinsey Global Institute analytics collated and integrated with more than 400 use cases across 19 industries and nine business functions. Before we go any further and analyze which markets are affected by AI and to what extent, let's discuss first what exactly Artificial Intelligence means. A large number of companies claim nowadays to incorporate some kind of "Artificial Intelligence" in their applications or services. But artificial intelligence is only a broader term which describes applications when a machine mimics "cognitive" functions that humans associate with other human minds, such as "learning" and "problem-solving".

The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle). We monitor validity of mappings from sensor inputs to actuator commands, controller-focused anomaly detection (CFAM), and from actuator commands to sensor inputs, system-focused anomaly detection (SFAM). CFAM is an image conditioned energy based generative adversarial network (EBGAN) in which the energy based discriminator distinguishes between proper and anomalous actuator commands. SFAM is based on an action condition video prediction framework to detect anomalies between predicted and observed temporal evolution of sensor data. We demonstrate the effectiveness of the approach on our autonomous ground vehicle for indoor environments and on Udacity dataset for outdoor environments.

Generating paraphrases, that is, different variations of a sentence conveying the same meaning, is an important yet challenging task in NLP. Automatically generating paraphrases has its utility in many NLP tasks like question answering, information retrieval, conversational systems to name a few. In this paper, we introduce iterative refinement of generated paraphrases within VAE based generation framework. Current sequence generation models lack the capability to (1) make improvements once the sentence is generated; (2) rectify errors made while decoding. We propose a technique to iteratively refine the output using multiple decoders, each one attending on the output sentence generated by the previous decoder. We improve current state of the art results significantly - with over 9% and 28% absolute increase in METEOR scores on Quora question pairs and MSCOCO datasets respectively. We also show qualitatively through examples that our re-decoding approach generates better paraphrases compared to a single decoder by rectifying errors and making improvements in paraphrase structure, inducing variations and introducing new but semantically coherent information.

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models. In this work, we use ideas from causal inference to describe a general framework to reason over CNN models. Specifically, we build a Structural Causal Model (SCM) as an abstraction over a specific aspect of the CNN. We also formulate a method to quantitatively rank the filters of a convolution layer according to their counterfactual importance. We illustrate our approach with popular CNN architectures such as LeNet5, VGG19, and ResNet32.