Avatar

Agnieszka Mikołajczyk-Bareła

PhD & Senior AI Engineer

Chaptr.AI

Biography

Researcher, programmer and AI expert with a solid experience in the industry. Currently working as a Senior AI Engineer at Chaptr.AI, developing large language models and AI assistants. Previously, as NLP Team Leader at Voicelab.AI, led the team that designed and trained TRURL, the first ChatGPT alternative in Poland. Successfully defended PhD at Gdańsk University of Technology on detecting and reducing the impact of errors and biases in AI data and models.

With over 2500 citations on Google Scholar, Dr. Mikołajczyk has contributed to numerous research projects and publications in machine learning, focusing on bias detection, explainable AI, and natural language processing. She has led multiple AI for Good initiatives, including HearAI for sign language recognition and DetectWaste for environmental applications.

Interests

  • Large Language Models
  • Explainable Artificial Intelligence
  • Bias Detection & Mitigation
  • Image Analysis
  • Deep Learning

Education

  • PhD in Machine Learning, 2017 - 2022

    Gdańsk University of Technology

  • MEng in Control Theory, 2016 - 2017

    Gdańsk University of Technology

  • BSc in Automation Control and Robotics, 2012 - 2016

    Gdańsk University of Technology

Projects & Experience

Professional work and research initiatives

*

Senior AI Engineer at Chaptr.AI

Working with AI assistants, LLMs, LLM-based agents, RAG, and others. Currently working in the book metadata optimization project.

Detecting and Reducing Bias in Data

Currently, in contrast to shallow models exploited in the past, most deep learning systems extract features automatically, and to do …

DetectWaste and ClassifyWaste

The proposed classify-waste benchmark is a merged collection of publicly available datasets with eight classification labels. The …

HearAI

Deaf people are affected by many forms of exclusion, especially now in the pandemic world. HearAI aims to build a deep learning …

Punctuation Restoration

Speech transcripts generated by Automatic Speech Recognition (ASR) systems typically do not contain any punctuation or capitalization. …

Tiny Hero - Generating pixel characters with GANs

Dataset TinyHero includes 64x64 retro-pixel character. All characters were generated with Universal LPC spritesheet by makrohn. Each …

Skin Lesion Classification

In the last twenty years the interest of automated skin lesion classification dynamically increased partially because of public …

Bird Song Classification

Sound-Based Bird Classification using Convolutional Neural Networks and Mel-Cepstrum Sepctrograms

Detect waste in Pomerania

Using detection models to localize and classify waste on images and video.

Hack4Environment

Hackathon. Let's do something for our environment.

Datasets

ML data collections

.js-id-datasets

DetectWaste and ClassifyWaste

The proposed classify-waste benchmark is a merged collection of publicly available datasets with eight classification labels. The …

Punctuation Restoration

Speech transcripts generated by Automatic Speech Recognition (ASR) systems typically do not contain any punctuation or capitalization. …

Tiny Hero - Generating pixel characters with GANs

Dataset TinyHero includes 64x64 retro-pixel character. All characters were generated with Universal LPC spritesheet by makrohn. Each …

Recent & Upcoming Talks

AI, Acoustics & Ornithology for sound-based bird classification

Have you ever wondered about the name of the bird you just heard singing? A group of women from local Polish chapter of Women in …

Introduction to Explainable AI: why should we understand AI decisions?

Is XAI really that important? Why should we try to explain our models’ predictions? A short introduction to explainable AI.

Brief introduction to XAI

Brief introduction to visual local explainabiliy methods - Local Interpretable Model-Agnostic Explanations (LIME), Layer-wise Relevance …

Recent Publications

(2023). Transferable Keyword Extraction and Generation with Text-to-Text Language Models. In ICCS.

URL

(2022). Deep learning-based waste detection in natural and urban environments. Waste Management.

PDF

(2021). A Comprehensive Analysis of Deep Neural-Based Cerebral Microbleeds Detection System. Electronics.

PDF

(2021). Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios. arXiv preprint arXiv:2109.06103.

PDF

(2021). PolEval 2021 Task 1: Punctuation Restoration from Read Text. Proceedings ofthePolEval2021Workshop.

PDF

Contact

  • Gabriela Narutowicza 11/12, Gdańsk, GDA 80244
  • Enter faculty of Electrical and Control Engineering Building and take the stairs to Office 207 on Floor 2