Sequence models brought about a revolution in speech recognition as Word Error Rate (WER) dropped significantly. This enabled the rise of several products like Alexa, Apple Siri, Google Voice Assistant etc.
However, sequential data is not just limited to speech. Several other daily activities linked to text, financial data, audio, video streams etc. also produce sequence data.
Deep learning models before RNNs were extremely useful for data with spatial dependencies.
However their results were not as promising with sequence data. This was mainly because they failed to capture the temporal dependence in the data which was more important than the spatial content.
RNNs solve this problem by adding internal memory. The capacities of traditional neural networks are bolstered with this addition and the results outperform the conventional ML techniques wherever the temporal dynamics are more important.
In this full-day immersive workshop, participants will develop an intuition for sequence models through hands-on learning along with the mathematical premise of RNNs.
 
2 favorite thumb_down thumb_up 0 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist
 

Outline/Structure of the Workshop

  1. Prerequisites Review
  2. Optimization Techniques in Deep Neural Network
  3. Building blocks of Artificial Neural Networks
  4. Back-propagation Algorithm
  5. Sequence Models
  6. Converting base models to recurrent form
  7. Case Study & Live Coding Exercise: Genomics
  8. Adding Long Term Memory to Recurrent Neural Nets via Gates: The GRU Model
  9. Selective Information Retention: The LSTM Model
  10. Advanced Coding Exercise: Combining everything together

Learning Outcome

Participants will

  1. Gain insight into the mathematical premise of sequence models
  2. Develop an intuitive understanding of sequence models.
  3. Know how to develop and apply sequence models for text, genomics and time-series data

Target Audience

Anyone who is interested in learning how to effectively gain insights in sequence data

Prerequisites for Attendees

There are no specific prerequisites.
The hands-on exercises would be in python, so some familiarity with python would make it easier for the participants to move through the exercises.
Knowledge about ANN is recommended but not a necessity, we will give an overview of the relevant theory.

schedule Submitted 1 week ago

Public Feedback

comment Suggest improvements to the Speaker

  • Liked Anant Jain
    keyboard_arrow_down

    Anant Jain - Adversarial Attacks on Neural Networks

    Anant Jain
    Anant Jain
    Co-Founder
    Compose Labs, Inc.
    schedule 2 months ago
    Sold Out!
    45 Mins
    Talk
    Intermediate

    Since 2014, adversarial examples in Deep Neural Networks have come a long way. This talk aims to be a comprehensive introduction to adversarial attacks including various threat models (black box/white box), approaches to create adversarial examples and will include demos. The talk will dive deep into the intuition behind why adversarial examples exhibit the properties they do — in particular, transferability across models and training data, as well as high confidence of incorrect labels. Finally, we will go over various approaches to mitigate these attacks (Adversarial Training, Defensive Distillation, Gradient Masking, etc.) and discuss what seems to have worked best over the past year.

  • Liked Dipanjan Sarkar
    keyboard_arrow_down

    Dipanjan Sarkar - Explainable Artificial Intelligence - Demystifying the Hype

    Dipanjan Sarkar
    Dipanjan Sarkar
    Data Scientist
    Red Hat
    schedule 3 months ago
    Sold Out!
    45 Mins
    Tutorial
    Intermediate

    The field of Artificial Intelligence powered by Machine Learning and Deep Learning has gone through some phenomenal changes over the last decade. Starting off as just a pure academic and research-oriented domain, we have seen widespread industry adoption across diverse domains including retail, technology, healthcare, science and many more. More than often, the standard toolbox of machine learning, statistical or deep learning models remain the same. New models do come into existence like Capsule Networks, but industry adoption of the same usually takes several years. Hence, in the industry, the main focus of data science or machine learning is more ‘applied’ rather than theoretical and effective application of these models on the right data to solve complex real-world problems is of paramount importance.

    A machine learning or deep learning model by itself consists of an algorithm which tries to learn latent patterns and relationships from data without hard-coding fixed rules. Hence, explaining how a model works to the business always poses its own set of challenges. There are some domains in the industry especially in the world of finance like insurance or banking where data scientists often end up having to use more traditional machine learning models (linear or tree-based). The reason being that model interpretability is very important for the business to explain each and every decision being taken by the model.However, this often leads to a sacrifice in performance. This is where complex models like ensembles and neural networks typically give us better and more accurate performance (since true relationships are rarely linear in nature).We, however, end up being unable to have proper interpretations for model decisions.

    To address and talk about these gaps, I will take a conceptual yet hands-on approach where we will explore some of these challenges in-depth about explainable artificial intelligence (XAI) and human interpretable machine learning and even showcase with some examples using state-of-the-art model interpretation frameworks in Python!

  • Liked Dat Tran
    keyboard_arrow_down

    Dat Tran - Image ATM - Image Classification for Everyone

    Dat Tran
    Dat Tran
    Head of Data Science
    idealo.de
    schedule 2 months ago
    Sold Out!
    45 Mins
    Talk
    Intermediate

    At idealo.de we store and display millions of images. Our gallery contains pictures of all sorts. You’ll find there vacuum cleaners, bike helmets as well as hotel rooms. Working with huge volume of images brings some challenges: How to organize the galleries? What exactly is in there? Do we actually need all of it?

    To tackle these problems you first need to label all the pictures. In 2018 our Data Science team completed four projects in the area of image classification. In 2019 there were many more to come. Therefore, we decided to automate this process by creating a software we called Image ATM (Automated Tagging Machine). With the help of transfer learning, Image ATM enables the user to train a Deep Learning model without knowledge or experience in the area of Machine Learning. All you need is data and spare couple of minutes!

    In this talk we will discuss the state-of-art technologies available for image classification and present Image ATM in the context of these technologies. We will then give a crash course of our product where we will guide you through different ways of using it - in shell, on Jupyter Notebook and on the Cloud. We will also talk about our roadmap for Image ATM.

  • Liked Varun Sharma
    keyboard_arrow_down

    Varun Sharma - Blockchain with Machine Learning - The ultimate industry disruptor

    Varun Sharma
    Varun Sharma
    Sr. Manager
    Sapient
    schedule 3 days ago
    Sold Out!
    45 Mins
    Talk
    Beginner

    The fusion of blockchain and machine learning is an ultimate game changer. Machine learning relies on high volume of data to build models for accurate prediction. A lot of the challenges incurred in getting this data lies in collecting, organizing and auditing the data for accuracy. This is an area that can significantly be improved by using blockchain technology. By using smart contracts, data can be directly and reliably transferred straight from its place of origin. Smart contracts could, however, improve the whole process significantly by using digital signatures.

    Blockchain is a good candidate to store sensitive information that should not be modified in any way. Machine learning works on the principle of “Garbage In, Garbage Out,” which means that if the data that was used to build a prediction model was corrupted in any way, the resultant model would not be of much use either. Combining both these technologies creates an industry disruptor which leverages the power of both Blockchain and Machine learning.

  • Liked Varun Sharma
    keyboard_arrow_down

    Varun Sharma - Automated Machine Leaning - Transforming the AI Landscape

    Varun Sharma
    Varun Sharma
    Sr. Manager
    Sapient
    schedule 1 week ago
    Sold Out!
    45 Mins
    Talk
    Intermediate

    Automated Machine Learning (AutoML) provides methods and processes to automate the end-to-end machine learning workflow towards solving real-world business problems.

    In traditional machine learning world, data scientist used to spend a considerable amount of time in Data wrangling, model selection and tuning, now with the advances of AutoML it provides methods and processes to make Machine Learning available for non-Machine Learning experts, to improve efficiency of Machine Learning and to accelerate research on Machine Learning.

    Automating the end-to-end process of applying machine learning offers the advantages of producing simpler solutions, faster creation of those solutions, and models that often outperform models that were designed by hand.

  • Liked Dr. Saptarsi Goswami
    keyboard_arrow_down

    Dr. Saptarsi Goswami - Meta features and clustering based approaches for feature selection

    45 Mins
    Tutorial
    Beginner

    Feature selection is one of the most important processes for pattern recognition, machine learning and data mining problems. A successful feature selection method facilitates improvement of learning model performance and interpretability as well as reduces computational cost of the classifier by dimensionality reduction of the data. Feature selection refers to the retention of discriminatory features while discarding the redundant and irrelevant features. In this process, a subset of D features are selected from a set of N features (D<N). There is another way of achieving dimensionality reduction by projecting higher dimensional data to lower dimension, normally referred to feature extraction. This thesis refers to the former one i.e. feature subset selection. Optimal feature subset selection method comprises of developing 1) an evaluation function for measuring the goodness of a feature or a feature subset and 2) a search algorithm to find out the best subset of features from all possible subsets of the whole feature set. Based on the nature of the objective function used in the search algorithms, feature subset selection algorithms are broadly classified into filter approach and wrapper approach. Classifier dependent wrapper approaches use classifier accuracy as the objective function while filter approaches use any evaluation function representing the intrinsic characteristics of the data set and the resulting feature subset works equally well for any classifier. This work focusses on filter based feature subset selection approach. In this work, initially a study has been done with currently available search based filter type feature selection algorithms for supervised as well as unsupervised classification with both the single objective and multi-objective evaluation functions. Some improvements over the current algorithms have been proposed and their efficiency has been examined by simulation experiments with bench mark data sets. In the second step, an inexpensive feature evaluation measure based on feature relevance to be used with a filter type feature selection for unsupervised classification has been proposed. It has been noticed during literature study that the concept of feature relevance in case of unsupervised classification is difficult to form and current methods are complex and time consuming. The proposed measure which considers individual variability as well as overall variability of the dataset,is found to be effective compared to the current methods by simulation experiments with bench mark data sets. Thirdly, it seems that the most of the current feature selection algorithms are based on search strategies to find out the best feature subset from the available feature set. For a large number of features, exhaustive search is computationally prohibitive which leads to combinatorial optimization problem and some sort of heuristic is used for the solution. With the increase of the number of features, the computational time for optimal feature subset selection increases.An alternative solution to this problem is to use clustering of the features to find out the best feature subset which is not yet explored sufficiently. In this work, an efficient clustering based feature selection algorithm has been proposed and simulation experiments have been done with bench mark data sets. The main contributions of the proposed algorithm are introduction of a novel method to determine the optimal number of clusters, a way of interpretation of the importance of the feature clusters and a method of selection of the final subset of features from the feature clusters. Finally, it is found that though lots of feature selection algorithms are available, it is very difficult to decide which algorithm is suitable for a particular real world application. Here a study has been done to establish the relation between the feature selection algorithm and the characteristics of the data set. A technique has been proposed to define a data set according to its intrinsic characteristics represented by some meta-features. Finally a feature selection strategy is recommended based on the characteristics of the data set and has been implemented with bench mark data sets to judge its effectiveness.

  • Liked Rahee Walambe
    keyboard_arrow_down

    Rahee Walambe / Aditya Sonavane - Can AI replace Traditional Control Algorithms?

    45 Mins
    Case Study
    Beginner

    As the technology progresses, the control tasks are getting increasingly complex. Employing the targeted algorithms for such control tasks and manually tuning them by trial and error (as in case of PID), is a cumbersome and lengthy process. Additionally, methods such as PID are designed for linear systems, however, all the real world control tasks are inherently non-linear in nature. With such complex tasks, using the conventional linear control methods approximates the nonlinear system to a linear model and in effect required performance is difficult to achieve.

    The new advances in the field of AI have presented us with techniques which may help replace the traditional control algorithms. Use of AI may allow us to achieve a higher quality of control on the nonlinear process, with minimum human interaction. Thus eliminating the requirement for a skilled person to perform meager tasks of tuning control algorithms with trial and error.

    Here we consider a simple case study of a beam balancer, where the controller is used for balancing a beam on a pivot to stabilize the ball at the center of the beam. We aim to implement a Reinforcement Learning based controller as an alternative to PID. We analyze the quality and compare the performance of PID-based controller vs. a RL-based controller to better understand the suitability for real-world control tasks.

  • Liked Tanay Pant
    keyboard_arrow_down

    Tanay Pant - Machine data: how to handle it better?

    Tanay Pant
    Tanay Pant
    Developer Advocate
    Crate.io
    schedule 2 months ago
    Sold Out!
    45 Mins
    Talk
    Intermediate

    The rise of IoT and smart infrastructure has led to the generation of massive amounts of complex data. Traditional solutions struggle to cope with this shift, leading to a decrease in performance and an increase in cost. In this session, I will talk about time-series data, machine data, the challenges of working with this kind of data, ingestion of this data using data from NYC cabs and running real time queries to visualise the data and gather insights. By the end of this session, you will be able to set up a highly scalable data pipeline for complex time series data with real time query performance.

  • Liked Parul pandey
    keyboard_arrow_down

    Parul pandey - Jupyter Ascending : The journey from Jupyter Notebook to Jupyter Lab

    Parul pandey
    Parul pandey
    Data Science Communicator
    -
    schedule 3 weeks ago
    Sold Out!
    45 Mins
    Demonstration
    Beginner

    For many of the researchers and data scientists, Jupyter Notebooks are the de-facto platform when it comes to quick prototyping and exploratory analysis. Right from Paul Romer- the Ex-World bank chief Economist and also the co-winner 2018 Nobel prize in Economics to Netflix, Jupyter Notebooks are used almost everywhere. The browser-based computing environment, coupled with a reproducible document format has made them the choice of tool for millions of data scientists and researchers around the globe. But have we fully exploited the benefits of Jupyter Notebooks and do we know all about the best practises of using it? if not, then this talk is just for you.

    Through this talk/demo, I'll like to discuss three main points:

    1. Best Practises for Jupyter Notebooks since a lot of Jupyter functionalities sometimes lies under the hood and is not adequately explored. We will try and explore Jupyter Notebooks’ features which can enhance our productivity while working with them.
    2. In this part, we get acquainted with Jupyter Lab, the next-generation UI developed by the Project Jupyter team, and its emerging ecosystem of extensions. JupyterLab differs from Jupyter Notebook in the fact that it provides a set of core building blocks for interactive computing (e.g. notebook, terminal, file browser, console) and well-designed interfaces for them that allow users to combine them in novel ways. The new interface enables users to do new things in their interactive computing environment, like tiled layouts for their activities, dragging cells between notebooks, and executing markdown code blocks in a console and many more cool things.
    3. Every tool/features come with their set of pros and cons and so does Jupyter Notebooks/Lab and it is equally important to discuss the pain areas along with the good ones.
  • Liked JAYA SUSAN MATHEW
    keyboard_arrow_down

    JAYA SUSAN MATHEW - Breaking the language barrier: how do we quickly add multilanguage support in our AI application?

    JAYA SUSAN MATHEW
    JAYA SUSAN MATHEW
    Sr. Data Scientist
    Microsoft
    schedule 3 months ago
    Sold Out!
    20 Mins
    Talk
    Intermediate

    With the need to cater to a global audience, there is a growing demand for applications to support speech identification/translation/transliteration from one language to another. This session aims at introducing the audience to the topic and how to quickly use some of the readily available APIs to identify, translate or even transliterate speech/text within their application.