Haider Raza

Haider Raza

Senior Lecturer in Artificial Intelligence, School of Computer Science and Electronics Engineering, University of Essex

Talks, Tutorials, and Seminars (Knowledge Exchange Activities)

Learning under Different Training and Testing Distributions

August 04, 2021

Tutorial, IADS: Data Science and Decision Making Summer School, University of Essex, 2021, Colchester, UK

In this talk, I will focus on the Learning under Different Training and Testing Distributions. Systems based on machine learning methods often suffer a major challenge when applied to the real-world datasets. The conditions under which the system was developed will differ from those in which we use the system. Few sophisticated examples could be email spam filtering, stock prediction, health diagnostic, and brain-computer interface (BCI) systems, that took a few years to develop. Will this system be usable, or will it need to be adapted because the distribution has changed since the system was first built? Apparently, any form of real-world data analysis is cursed with such problems, which arise for reasons varying from the sample selection bias or operating in non-stationary environments. This tutorial will focus on the issues of dataset shifts (e.g. covariate shift, prior-probability shift, and concept shift) and will cover transfer learning for managing to learn a satisfactory model.

Introduction to Deep Learning & Neural Networks

July 27, 2021

Tutorial, IADS: Data Science and Decision Making Summer School, University of Essex, 2021, Colchester, UK

In this talk, I will focus on the Introduction to Deep Learning & Neural Networks. Day 1 tutorial will focus on convolutional neural networks, also known as convnets, a type of deep-learning model almost universally used in computer vision applications. You’ll learn to apply convnets to image-classification problems—in particular, those involving small training datasets, which are the most common use case if you aren’t a large tech company.
Day 2 tutorial will focus on deep-learning models that can process text (understood as sequences of word or sequences of characters), time-series, and sequence data in general. The two-fundamental deep-learning algorithms for sequence processing are recurrent neural networks and 1D convnets. The applications of these algorithms are in document classification, time series classification, sequence to sequence learning and sentiment analysis.

Python Intro Course

July 26, 2021

Tutorial, IADS: Data Science and Decision Making Summer School, University of Essex, 2021, Colchester, UK

In this talk, I will focus Python Intro Course. This Introduction to Python course is for beginners. We aim to introduce fundamental programming concepts using Google Colab. We will introduce variables, data types, casting, string, Boolean, operators, lists, tuples, loops, conditions, functions, and a bit of NumPy. This course is designed for those who are coming from a non-technical background and willing to learn Python to great in summer school.

[Keynote] Brain-Computer Interfacing

February 20, 2021

Keynote, International Conference on Computing, Communication, and Intelligent Systems, 2021, India

Delivered a Keynote speech at IEEE International Conference on Computing, Communication, and Intelligent Systems (Co-Sponsored by IEEE) organised by School of Engineering and Technology, Sharda University, Greater Noida, Uttar Pradesh, India held on 19th-20th February 2021. This talk was focused on Brain-Computer interfacing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I presented my research done during my PhD, Post-Doc, and Essex.

Brain-Computer Interfacing

October 27, 2020

Tutorial, BDG LifeSciences [Online], India

Guest Speaker at Envision with BDG Initiative of BDG Life-sciences and presented Brain-Computer interfacing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I presented my research done during my PhD, Post-Doc, and Essex. The talk is available at YouTube Watch me

Introduction to Deep Learning

July 31, 2019

tutorial, IADS Summer School, University of Essex, Colchester, Essex, England

In this talk, I have covered the topics given as follows:

Data Analysis and Predictive Analytics : Southend-on-Sea Borough Council (2-Days)

March 07, 2019

Tutorial, Civic Centre, Southend-on-Sea, Southend-on-Sea, UK

This talk tutorial covered Data Analysis and Predictive Analytics using R and R-Studio. In this training delegates were introduced to key R-packages for data visualisation, e.g.in terms of graphs and charts. We have also covered data loading from spreadsheets, data cleaning, feature-preparation, and training a basic predictive model. This workshop covered industry-led examples throughout. It was aimed that delegates having basic knowledge about R from the previous training.

Artificial Intelligence & Machine Learning

December 11, 2018

Talk, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, India, Hyderabad, India

This talk covers how AI and Machine Learning have changed since birth and who are key people behind it.

Artificial Intelligence & Machine Learning

December 10, 2018

Talk, Taj MG Road, Bengaluru, India, Bengaluru, India

This talk covers how AI and Machine Learning has changed since birth and who are key people behind it.

Web Scraping and Mining: Southend Council

November 06, 2018

Tutorial, University of Essex (Southend Campus), Southend, Southend, UK

This talk tutorial covered Introduction to Web Scraping and Mining using R-Studio.

Introduction to R: Southend County Council

October 25, 2018

Tutorial, University of Essex (Southend Campus), Southend, Southend, UK

This talk tutorial covered Introduction to R using R Studio: We also delivered a basic introduction to data analytics.

Introduction to R: Suffolk County Council

October 08, 2018

Tutorial, Suffolk County Council , Ipswich, Ipswich, UK

This talk tutorial covered Introduction to R using R Studio. We also delivered a basic introduction to data analytics.

Introduction to Python: Minerva Analytics Ltd

October 03, 2018

Tutorial, University of Essex, UK, Colchester, Essex

This talk tutorial covered Introduction to Python using Anaconda: Jupyter Notebook. We also delivered a basic introduction to data analytics.

Machine Learning and Data Science

August 25, 2018

Tutorial, Data Science Intense (DSI) Training Program 2018, African Institute for Mathematical Sciences, Cape Town, South Africa

The Data Science Intensive (DSI) program is an 8-week hands-on skills training data science course based on solving real-world problems. I have spent two week to deliver first session of this DSI program. I have focused to present on the following topics and we competed on a Kaggle dataset: Advance House Price Prediction

Learning Under Different Training and Testing Distributions

August 25, 2018

Tutorial, Big Data and Analytics Summer School-2018, University of Essex, Colchester, England

The Institute for Analytics and Data Science, University of Essex is hosting its annual Summer School 2014, bringing you two weeks of cutting-edge courses across the field of data science and analytics.

Learning Under Dataset Shifts

March 10, 2018

Talk, Integral University, Lucknow, India, Lucknow, India

Dataset shift is a challenging situation where the joint distribution of inputs and outputs differs between the training and test stages. Covariate shift is a simpler particular case of dataset shift where only the input distribution changes (covariate denotes input), while the conditional distribution of the outputs given the inputs p(y|x) remains unchanged. Dataset shift is present in most practical applications or reasons ranging from the bias introduced by experimental design, to the mere irreproducibility of the testing conditions at training time. For example, in an image classification task, training data might have been recorded under controlled laboratory conditions, whereas the test data may show different lighting conditions.

Non-Stationary Learning in EEG-based Brain-Computer Interface

May 10, 2017

Talk, Swansea University, Swansea, Wales

A common assumption in traditional supervised learning is the similar probability distribution of data between the training phase and the testing/operating phase. When transitioning from the training to testing phase, a shift in the probability distribution of input data is known as a covariate shift. Covariate shifts commonly arise in a wide range of real-world systems such as electroencephalogram-based brain–computer interfaces (BCIs). In such systems, there is a necessity for continuous monitoring of the process behavior, and tracking the state of the covariate shifts to decide about initiating adaptation in a timely manner. This talk focused on discussing methods to adapt to covariate shift.

Artificial Intelligence and its application in Brain-Computer Interface

April 10, 2017

Talk, Shri Ramswaroop Memorial Public School, Lucknow, India, Lucknow, India

This talk was focused on Brain-Computer interfaceing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I have discussed my research done during my PhD and Post-Doc.

Machine Learning and Brain-Computer Interface

August 10, 2014

Talk, Integral University, Lucknow, India, Lucknow, India

This talk was focused on Brain-Computer interfaceing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I have discussed my research done during my PhD and Post-Doc.