Machine Learning

CS-433

Robert West

9 Sep 2025
 Alternatives & complements
Master
Bachelor
CS-552 – Modern Natural Language Processing
CS-430 – Intelligent Agents CS-233 – Intro to ML
CS-439 – Optimization for ML CS-330 – Artificial Intelligence
CS-401 – Applied Data Analysis EE-311 – Fundamentals of machine learning
CS-500 – AI product management CIVIL-226 – Introduction to ML for engineers
CS-503 – Visual intelligence: machines and minds BIO-322 – Intro to ML for bioengineers
CS-526 – Learning theory ME-390 – Foundations of artificial intelligence
EE-559 – Deep Learning
CIVIL-459 – Deep learn. for autonomous vehicles
EE-411 – Fundamentals of inference and learning Seminars, Doctoral Courses and continued education
MGT-418 – Convex optimization PHYS-754 – Lecture series on scientific ML
MATH-403 – Low-rank approximation techniques CS-612 – Topics in Natural Language Processing
MATH-412 – Statistical ML EE-613 – ML for engineers
DH-406 – ML for Digital Humanities ENG-704 – EECS Seminar: Advanced Topics in ML
EE-556 – Mathematics of data CS-723 – Topics in ML Systems
CS-502 – Deep learning in biomedicine EE-608 – Deep Learn. for Natural Language Proc.
MICRO-455 – ML I EPFL Extension School – Applied Data Science: ML
MICRO-401 – ML Programming
MICRO-570 – ML II Research talks: join mailing list:
ml@[Link] .ch on [Link] .ch
fl
fl
 Course Logistics
Assessment

✤ Project 1 (10%), due 31 Oct

✤ Project 2 (30%), due 18 Dec
✤ Final exam (60%)
 Course Logistics
Lectures

Tuesday 16:15-18:00: 2x45mins, Room: Rolex Learning Center

Wednesday 10:15-12:00: 2x45mins, Room: Rolex Learning Center

We provide PDF lecture notes on our webpage and GitHub, and

video recordings of all lectures available
 Course Logistics

Lectures
tentative
schedule
 Course Logistics
Exercises

Thursday 14:15 - 16:00 - live interaction!

Rooms: CO123, INF1, INF119, INJ218, INM202, INR219
assignment by SCIPER number, see course info sheet PDF

All labs and projects are in Python.

See the rst lab to get started.

Code Repository for Labs: [Link]/epfml/ML_course

fi
 Course Logistics
Team of assistants contact us: online forum!

PhD students MS students

Alexander Hägele • Atli Kosson • Adam Mesbahi Amrani • Ahyoung Seo • Efe
Dongyang Fan • Francesco D’Angelo • Tarhan • Eren Akçanal • Francesco Bellotto •
Gizem Yüce • Hristo Papazov • Oguz Igor Pavlović • Jacques Mandriota • Jingxuan
Yüksel • Bettina Messmer • Diba Hashemi • Sun • Leonardo Martella • Michele
Justin Samuel Deschenaux • Mohammad Lanfranconi • Mikulas Vanousek • N'Zian
Hossein Amani • Saibo Geng Cédric Kof • Shunchang Liu • Vincenzo
Sigillo' Massara • Xinran Li • Yassine
Mustapha Wahidy • Zhuofu Zhou
fi
 Course Logistics
Projects

✤ Project 1 (10%), due 31 Oct

✤ Project 2 (30%), due 18 Dec

Real-world problems, Python, Groups of 3 Students

 What to expect?

✤ overview over ML/AI

✤ basic understanding of most important ML methods
and fundamental concepts
✤ experience how ML is done on a practical problem
 What not to expect?

✤ instantly becoming an expert data scientist / ML

researcher / statistician / large-scale ML specialist /
ML software expert / domain expert

✤ learn about that newest hack you saw on blog xyz.

 Introduction

What is Machine Learning?

What is Machine Learning?

algorithms that can

learn from data

 traditions…

data
traditional
output
programming
rules

data
ML rules
desired
output ML model
weights w
 traditions…
test
data ML
output
testing

training
data ML
rules
desired training
output ML model
weights w
 Learning Functions from Data

pixels
input output
image
hussar monkey
classi cation

“Bonjour! Comment
text

“Hello! how are you?” translation

allez-vous?”
audio

“Hello! how are you?” speech to text

pixels

“a dog is sitting at the beach image

next to another dog” captioning

writing
text

wha…t?
assistant
fi
 input output
“moon landing webpage 1
webpage 2 web search
conspiracy”
webpage 3
browsing history on recommender
fashion website system

medical image
pixels

melanoma
processing

“look at whether it works for

video

lip reading
the UK or not”
The bot must be trained in a language capable of decoding Python's
strings and displaying it on a high quality display, in order to be able
“moon landing to produce what they have learned in English, and indeed, these
images, have been uploaded to the web for quite some time. If this
type of thing is indeed present in the wild, then what sort of wild bot
should I be worried about? text generation
conspiracy…” Thanks to this one speci c experiment performed on the same day - as
described by the author:
Using some kind of neural network to learn speech, and being able to
decode it in order to communicate with others (including yourself)
through its GUI

professional dancer
dance transfer
+ photo of myself [Link]
fi
image source
 Classi cation xi 2 R d

Training data
fi
 The Learning Algorithm xi 2 R d

(Stochastic
Gradient
Descent)
x
w := w + ·x
iteration cost: O(d)

Perceptron Support-Vector-Machine
(Rosenblatt 1957) (Cortes & Vapnik 1995)
 towards…
understanding intelligence
?
Machine Learning Neuroscience / HBP

vs
 What is the difference between
Artificial Intelligence, Data Mining,
Statistics, Machine Learning?
 AI X

Computer Statistics
Science Machine
Learning

Application
domain
 Job Skills

X
Machine Learning

Coding Math &

Skills Statistics
Data
Scientist
Software Traditional
Engineer Scientist

Application
domain
 why ML?

Applications
 Industry Applications

✤ majority of industries, originally not ‘digital’:

✤ agriculture, NGOs, ‘sharing economy', logistics,
delivery, services, manufacturing, sports,
personalized health, call centers, entertainment, …

✤ not only the

‘usual suspects’
 Applications in Other Sciences

✤ increasingly data driven

✤ … Psychology, Economics, Medicine, Social sciences
✤ science of X ➔ digital science of X

[Link]/wiki/Index_of_branches_of_science
ML is only a small part!
 History
✤ ML is not new!

London 1854
cholera outbreak
 History

✤ ML is not new!

✤ the early days - 1950s and 1960s

✤ Neural networks
✤ Turing
 “the emb
electroni r y o of an
What has changed? c compu
t e r that …
will be a
ble to wa
see, writ lk, talk,
3
1950s: 10 FLOPs e, reprod
and be co u ce itself
25 nscious o
2024: 10 FLOPs existence f its
.” 1958

*Llama 3.1 405B training was 3.8x10^25 ops

fl
 Challenges
✤ Hype
✤ cycles of AI popularity

✤ Data Ethics, Privacy, Fairness

Challenges
 Challenges
✤ Hype
✤ cycles of AI popularity

✤ Data Ethics, Privacy, Fairness

✤ Lack of Interpretability
✤ example: medical applications of deep learning

✤ Social Implications of AI
✤ impact and potential unsafe use (today’s models)
✤ e.g. impact on labor market, education, abuse, misinformation,…

✤ threats from Super-human AI (tomorrow’s models)

✤ see Nick Bostrom, Yuval Harari

need: Scientific Method, Reproducible

Research, Open Source and Open Data
 ML Applications
by CS- Master Students
4
3
3
 ML science projects by your colleagues
Machine Learning-based Estimation of Cardiac Contractility from Peripheral Pressure Waveform Regularized maximum likelihood estimation – TRANSP-OR
Deep learning techniques for geometric matching of C. Elegans brain microscopy images Stroke Level Estimation through pac-man game data played by acute stroke patients
Benchmarking Machine Learning Methods for Eukaryote/Prokaryote Contigs Classi cation STLM: Steganography in Text using Language Models
Machine Learning for Science: Classi cation of Skin Samples Using Mass Spectrometry Analysis Eastern Rituals Search Engine (ERSE)
Application of Deep Knockoffs for fMRI to Generate Surrogate Data Cough Classi er
Automatic detection of weak cipher usage in aircraft communications Extracting high value lung ultrasound images from video for the diagnosis and prognosis of COVID-19
Predicting Topic Change and Emoji Usage from Twitter Data Detecting rooftop available surface for installing PV modules in aerial images using Deep Learning
Cell Nuclei Segmentation in 2D Fluorescence Microscopy Images Dimensionality reduction and clustering of energy consumption time series in supermarket buildings
Unsupervised cell classi cation in ow cytometry data Protein-Protein Interactions
Predicting chemicals concentration in water streams using Gradient Boosting Regressor Predicting gene-gene relationship with CNNC model
Extracting Masonry Building Facades through Polygon Image Segmentation PneumoNet: Neural networks for the detection of pneumonia from digital lung auscultation audio
Sequence-dependent clustering of DNA in Protein-DNA Xray crystal data and in cgDNA+ model Predicting errors during Pacman for stroke patients
Applying the VoxelMorph Framework to [Link] Brain Data Galaxy Detection Machine Learning Project
Using forearm sEMG to control individual ngers of a robotic hand Automatic detection of available area for rooftop solar panel installations
Music beyond Major and Minor Prediction of myocardial infection risk after stenosis diagnosis
Avalanche Forecasting: An Ordinal Regression Approach LC3 compressive strength analysis
Machine Learning for Side-Channel Disassembly Adapting Attention Guided Camera Localization for the Geodetic Engineering Laboratory
Multi-object Detection and Tracking Machine learning models to predict the diagnosis and risk of COVID-19 from clinical data in Switzerland
Motion-based Similarity Search in Videos of Confucian Rituals Facades and Openings Detection Based on Different Deep Learning Models
Detecting the Degree of Cavitation In Situ in Young Trees Variational Inference compared to Markov Chain Monte Carlo for modelling gene expression
Machine Learning in Chemistry 3D Spatiotemporal clustering of mixed-type medical data in Tanzania
Personalized Federated Image classi cation using Weight Erosion Classi cation and Clustering on Schizophrenic Patient’s Data
In-crystal Gamma-interaction localization for positron emission tomography (PET) from Cherenkov photons TRANSP-OR – Prediction of mode of transportation
Classi cation of zebra sh embryo using various ML methods Learned cross-domain descriptors (LCD) for drone navigation
Resource-Ef cient Machine Learning Algorithm Design for On-Implant Neurological Symptom Detection What if Interactive GlobalCOVID Policy Simulator
Ebola Virus Disease Diagnosis for West African Ebola Virus epidemic Image Segmentation of Adenovirus Particles in Food Vacuoles of Eukaryotic Organisms
Supervised classi cation of y behaviors from posetracking data Music Beyond Major and Minor
Cell-type classi cation from microscope imaging Determining the important features for estimating the reproduction number in the COVID-19 pandemic
COVID-19 Predictions using Machine Learning Exploring chord embedding spaces between musical composers and eras
Unsupervised time series analysis of country wise COVID data Vector Embeddings of Musical Chords
Voxelmorph Word embeddings and transformer models for optimal learning
Unsupervised classi cation of video games styles Identi cation of re periods from air quality monitoring network measurements
Can the Style and Wording in Critical Reviews of Video Games Predict its PEGI Labelling? Drone and pigeon detection
Ensemble Methods for Dynamic Portfolio Valuation Characterization of turbulent structures in tokamaks
Vector embeddings of harmonies in music with deep learning Improving Deep Learning models for EMG decoding used for prosthesis control enhancement
Robustness of U-Net based models to common image artefacts Pneumonia Diagnosis based on CNN-LSTM-BERT Model
Recognizing Humor and Predicting Humor Ratings in Short Texts L-form bacteria segmentation
Segmentation of cell nuclei in 2D microscopy images with CNNs Machine Learning for Spaced Repetition in Human Learning
Mechanism of Action (MoA) Prediction – Kaggle Competition COVID-19 risk strati cation on Chest X-Rays: performance on a small cohort of patients in Switzerland
Diagnostic and Prognostic models for Ebola Dry vs Wet Cough Automatic Classi cation using the COUGHVID Dataset
Automatic Grading of Handwritten Student Essays Improving Freshwater Quality Measurements through Machine Learning
Stroke Level Prediction through Pacman Game Data Lesion detection on cardiology images using Deep Learning
Among Us Project 2 – Market states prediction 3D to 2D feature matching for next generation 3D mapping algorithms
Calibrate a model of OTC markets
fi
fi
fi
fi
fi
fi
fi
4
fi
fi
fi
fi
fi
fl
fl
fi
fi
fi
fi
fi
2
0
2
0
ML science projects by your colleagues
Probing EEG Signals with Neural-Network Classifiers The future of data storage: "Digital Polymers"
Learning from Re-Structured Knowledge in Pretrained Transformer Feed-Forward Layers Droplet Classification & Cell Counting
A System for Automating the Detection and Counting of Frogs in Small Passages Discrete traffic data generation using ML methods
Efficient CNN defect detection in sewer pipes with application of active learning Detecting TB from chest X-Rays in a population of patients living with HIV and diabetes in West Africa
Convolutional graph neural networks for tracking yeast cells Machine learning for predicting stimuli response in mice
U-Net for segmenting fascicles in vagus nerve histologies Modular Clinical Decision Support Networks for Data-Driven Diagnostic Predictions
The Best Location for You to Live Evaluating the performance of GANs on C. Elegans neural network images deformation
Severe vs Mild Cough Classification Exploring and Visualising Patterns in 300’000 Consultations Collected with a Clinical Decision Support Algorithm
Improving Chord Prediction in Jazz Music using Melody Information Mouse Action Segmentation
Identifying recrystallization in stainless steel using machine learning on accoustic data Music Super-resolution with Spectral Flatness Loss and HiFi-GAN discriminators
Socio-epidemiological insights from a yearlong COVID-19 Twitter stream Lego Project
Complete Sentence Detection for Speech Recognition Systems The LEGO Detection Project
Deformation of images using Generative Adversarial Networks: a study on neural activity data of the worm C. elegans Using GANs to deform 3D bodies
Predicting emotions from brain data using various machine learning models. Semantic Segmentation of Centrioles in Human Cells and Assigning Them to Nuclei
Optimization of a memory gene selection for annotating cell-families in scRNAseq data, a machine learning approach Finding meaning in autogenerated text
Wolf Howling Detection Droplet Counter
Machine Learning for Energy Expenditure Prediction Reconstruction of cell lineage with deep learning and cell state transition dynamic inference
Identifying Green Jobs Automatic detection of natural slicks in Lake Geneva from a ground-based optical imagery package
Surrogate modelling of nerve electrical stimulation using deep learning Delineating Solar Panels using Aerial Imagery
Improving Chord Prediction in Jazz Music Psychology takes on ML
Learning-based Correspondences for Ophthalmic Image Registration EcoML
Machine Learning replaces Radiative Transfer Exploring the feasibility of DNN models for the quantitative discrimination between different conformational species of α-synuclein
Deep Learning-based Discomfort Glare Detection Complex Valued Neural Networks
Network Architecture Search and Expert Designed CNNs for Multi-target Concrete Defect Detection Neuron and axon image detection
SKA Source finding A regression based approach of exploring the glare metrics using real world experiments data
Classification of ordinal outcomes for the analysis of injury severity using machine learning methods Ophthalmology Image Registration
Developing a ML pipeline to detect centrioles in human cells Move sequence detection on bouldering problems
If You Are Happy And You Know It, Your Speech Will Surely Show It: A CNN Based Speech Emotion Detector Understanding Bouldering using ML Methods
SELFIES or SMILES? A case study in chemical reaction prediction Generalizability of dysarthric speech detection models across languages and pathologies
Machine learning for flir temperature extraction Retinal image registration
Posture Detection for Healthy Desk Work Improving chord prediction in Jazz music using melody information
Tuberculosis Classification Survey using Computer Vision models Protein domain classification
Phosphorylation Site Prediction Using Deep Learning DNA Binding Sites Prediction
Unsupervised Topic Modeling Unsupervised Learning to Prescribe Medication to Schizophrenic Patients
Disambiguating Voynich Manuscript transliterations with word embeddings Plasma Mode Classification using 2D-Convolutional Neural Networks
Transformer network for the Dial-a-Ride problem Predicting Ions Concentration in Water Streams
Covert speech decoding from EEG signals Unsupervised Non-Deformable Retina Images Registration Using Neural Network
Stock Prediction using Sentiment Analysis Detecting novelty in USPTO patent applications with neural networks
Studying Lobbying Influence in the European Parliament using Twitter data Digitizing patents
Oscillation Classifier for a 2 dimension trajectory Fear Decoding in Rodents
Automation of tuft detachment detection for flow detachment analysis Combining Unsupervised and Supervised Learning Techniques for Prediction and Analysis of Rhône's Plume Shape
Predicting lobbying influence in the European parliament through retweet graphs Racing team - detection of cones
Predict mouse behaviour from LFP recordings Lung Ultrasound Covid Classification
Predicting the Coordination Environment of Zn metalloproteins Hydrometeor Classification and riming degree estimation from Multi-Angle Snowflake Camera images.
Approaches to DFT Parameter Learning Single amino acid prediction at protein-protein interaction interfaces
Effect of Loss Function on Supervised Learning of Quantum Many-Body States Reproduce test-time training algorithm on iWildCam dataset
ModalPINN - Reconstruction of airflow around a cylinder using limited number of sensors Towards Accurate Prediction of Donor-acceptor Copolymer Properties
Unsteady parametrized Stokes equations in a 2D arterial bifurcation with stenosis: design of an Autoencoder for data compression Word Embeddings for the Morphosyntactic Analysis of the Voynich Manuscript
4
2
0
2
1
 Novenzyme Stability Prediction (Kaggle Competition)
Estimating the robustness of deep learning fraud detection on the ethereum blockchain against attackers with a leaked model Building an ML model to determine tweet sentiment
ML4 Science Physics Informed Neural Networks Tweets Sentiment Analysis

ML science projects by your colleagues

CERN Zenodo - Adaptable Spam Filter Modelling Hit The Road Jack
Grokking - Reproducibility Report Fine-tuning a neural language model to address text constraints
Solving Road Segmentation using UNet Automated Inpaintings of Humans in Images
Wildfire Susceptibility Mapping Characteristics of different transcription factors
Modelling Energetic Particles in Matter Fine-tuning and Prompt-learning on Commonsense Causal Reasoning
HOPE-Generator Mandatory Lane Change Prediction
Crack Segmentation on FRP CT Images Using Residual Multi-scale Dilated Convolution and Reversed Cross Entropy Loss Magical Mandrills
Epilepsy Detection Reproducibility Study of Behavior Transformers
Rhe force applied by a standing wave acoustic levitator on small objects Predicting Social Media Sentiment: A Text Classification Approach
Predicting the Intelligence of a Person From a Video: A Deep Learning Approach Machine learning in finance: forecasting and trading
Using Machine Learning for the Prediction of Motor Impairment and Recovery in Stroke Deep Learning-Based Clustering of Images of Damaged Buildings
Firing rate prediction in optic nerve fibers GFP classification project
Optimal U-Net for Image Segmentation Team DTJ - Tweet sentimental analysis
Option B - Text classification Neural Network Architectures for Road Segmentation
Satellite Images Classification - Project 2 Tracking worms for reading minds by Andromeda
Solubility classification of molecules ML4Science - Training an LCD model on the KITTI dataset
Modelisation of electron diffusion in water for radiation therapy using Generative Adversarial Networks ML4Science: Mining Effective Words For Climate Change Communication
Sentiment Analysis on Tweets Automatic segmentation of nerve histological section - TNE lab
Brain Fingerprinting and Task Decoding via Graph Structure Learning Prediction of fractional flow reserve based on CT scan images and lesion masks of coronary arteries
Aerospace Bearing Composer Classifier on MuseScore Sheet Music
Fear classification from physiological information using knowledge distillation Adaptive Quantization for 6DoF Pose Estimation
Predicting apartment demand using Machine Learning models Deep hedging (reproducibility challenge)
Cells and Pili Detection on ISCAT images Exchange Rate Forecasting with Neural Networks
Brain Fingerprinting: Identifying Individuals via learned brain graphs Physics-informed neural networks for a system of discrete masses and springs
Doping detection using athlete's biological passports Semantic Road Segmentation using combination of high spatial resolution Neural Network model
Autonomous Lane Changing using Deep Reinforcement Learning with Graph Neural Networks Road segmentation
Sea ice coverage Multitask learning for harmodynamics
Reproducibility Study of ”Scaled-YOLOv4: Scaling Cross Stage Partial Network” Reproducibility Challenge of the paper: Numerical influence of ReLU’(0) on backpropagation
Centriole elimination program in C. elegans Text Sentiment Classification Project
Image Road Segmentation Deep Learning-Based Dysarthric Speech Classification In Adverse Acoustic Environments
Towards Commonsense Causal Reasoning with Large Language Models Report For Text Sentiment Classification
Probe Posture Prediction Vote Prediction Algorithm - Valais Constituante
Reproducibility Study of ``Assessing Generalization via Disagreement'' Modular Decision Support Networks (MoDN) to predict respiratory disease from lung sounds
ML project with the Laboratory of the Physics of Biological Systems Predicting poverty through time with publicly available data
Optimization of Biological Age Prediction from Brain Anatomical Volume Measurements using Subgrouping Models Censorship of Twitter - Unsupervised Topic Modeling
Do CNNs and Vision Transformers learn visual representations similar to those of the monkey brain? A New 1D CNN Method to detect Sleep Apnea using a single-lead ECG signal
Fine-tuning DeepLabv3 as a Road Segmentor for Satellite Images Combinatorial optimization with Autoregressive Neural Networks
Evaluating the Performance of the U-Net CNN for Road Segmentation in Satellite Images Classification of Tweets based on Censorship
A convolutional neural network segmenting fission yeast microscopy images Patent Classification into Sustainable Development Goals defined by the United Nations.
Bias Slayer: AI4Health - Spotting biased applications Intrusion Detection System for Blockchain Transactions
Prognostic models on an international data set of 800'000 patients suspected of COVID-19 latecommers Finding relevant gene for centriol assembly and desasembly in [Link]
Language Proficiency and Authorship Classification Strength Modelling of the neutral hydrogen in galaxies with a Fully-Connected Neural Network
Predicting Housing Demand Budding and Fission Yeast Segmentation
Segmentation of fission yeast microscopy images Predicting Depression From Passive Phone Data - NoCommonPoint -SMSL
On the Limits of Human-centered Commonsense in Large Language Models Multimodal Deep Learning for a Global data set of COVID-19 Patients
Cell segmentation using time-sequence data Explaining the Valais Constituent Assembly Votes
Automated Forensic Ink Recognition via MSP Analysis Andasi Project 2: Predicting Myocardial Infarction from In Silico Data Using Transfer Learning
Predicting if two frames are part of the same video Machine Learning in Quantitative Finance - Fast Derivatives Pricing and Hedging
Natural Language processing: Twitter sentiment analysis Improving Causality Understanding of Trajectory Prediction Models Using Contrastive Learning
Reproducibility Study of ”Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design” Sleep Stage Classification through Non-Invasive Sensors
Improving 3D cell segmentation in whole-brain imaging MultiModal Modular Network (MoMoNet) for predicting COVID diagnosis from mixed image and tabular data
Label-free identification of neurodegenerative aggregates using Deep Learning Novelty Detection and Revenue Estimation
Detection of protein aggregates in neural cells in Parkinson's disease Deep Learning for Edge-AI Respiratory Disorder Monitoring
Worm tracking for personality detection Novelty Detection in the Dotcom Bubble
Decoding Brain States Triggered via Video Game with fMRI Based MVPA Approach Reproducing results for Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization method
4
2
0
2
2
ML science projects by your colleagues
Image-based Cell Cycle Phase Classification using Machine-Learning Techniques Protein fitness landscape & optogenetic design
Generalist neural networks for segmenting microscopy images
ML For Three Trees II - 🌳 🌲 🌴 Machine Learning for chess moves recognition
Text Classification by Team: AI_squad State space modeling of memory representations in the hippocampus
Learning phase masks for lensless imaging Data-driven surrogate modeling of the hemodynamics by prediction of POD coefficients
Swiss Plasma Center: Investigation of the operational parameters for QCE H-mode regime access in TCV plasmas with supervised learning Explaining venture teams’ opportunity identification through multimodal data
ML4Science - Deep learning image classification for cell cycle stages Commonsense Persona-Grounded Dialogue Challenge (CPDC 2023)
Road segmentation using deep learning Machine Learning Based Spherical Deconvolution for Intra-Voxel Fiber Estimation and Brain Connectivity Mapping
Recovering HDR signals from LDR images for understanding contrast preservation for view-out research Efficiency of BlazePose markless pose estimation
Data-driven surrogate modeling of the hemodynamics by prediction of POD coefficients (3D Navier-Stokes equations) Exploring Brain Modulation: Opto-fMRI Decoding of Locus Coeruleus Firing Patterns Using Searchlight, Multiple Kernel Learning, and
Advancing Homepage2Vec with LLM-Generated Datasets for Multilingual Website Classification Exploring Neural Scaling Law for Deep Neural Network Models of the Ventral Visual Stream
Data-driven Marketing Strategies for Non-Profit Organizations Deep Biometric Fingerprint Matching
Reinforcement Learning Actor for Blade Pitch Control in Wind Turbine Systems Advancing R&D Expenditure Predictions: The Power of Google Trends Data in Nowcasting
Classification of Hsp70 proteins into taxonomic groups based on their amino acid sequences Physiotherapy Exercises and Errors Classification
Project2 ML_hype Machine Learning Force Fields (ML-FFs) from Spatial Equivariant Descriptors
Predicting mortgage default in the US Comparison of Five Methods to Twitter Sentiment Analysis
Synthetic data generation with VAE for fairness mitigation Benchmarking models for cell location recovery from single cell transcriptomics
Comparing U-Net and DeepRoadNet architecture to a generic CNN baseline for road segmentation LLM Personalities Shenanigans
Text Sentiment Classification Biofilll: Evaluating Extreme Reconstruction and Inpainting on Biological Imaging
Fine-tuning open-source LLMs for argument detection Topological analysis of Drosophila neural cultures
Twiter Text Classification Clustering of DNA Sequences for Primer Extraction
ML4Science WhAI Beyond additive noise: Evaluating Style Geometric Style Transfer in Scene Text Recognition
Urban Heat Island intensity prediction using ensemble regression methods Characterization and automatic differentiation between minor and major disruptions
Protein Thermal Stability Prediction Automated Informalization Using LLemma
Road Segmentation - Team SLO RainetteX_project - Markerless Pose Estimation
Reproduction and Adaptation of Epileptic Seizure Detection Algorithm into Standardization Framework ML4S - Train generalist deep neural networks with database of annotated images
Investigation of the operational parameters for QCE H-mode regime access in TCV plasmas with supervised learning A Dual-Task Pipeline for Predicting Optic Nerve Neuron Firing Patterns
Satellite Image Road Segmentation with an Adapted ResNet34 Implementation Optimisation of question selectionfor long term memory retention using machine learning
Knowledge Tracing: Comparing DNNs Versus GPT For Intelligent Tutoring Systems Rethinking Optimization for Non-Convex problems with SCRN and its derivatives
Optimizing Beam Dynamics in LHC Enhancing Home Physiotherapy: Machine Learning for Exercise Recognition and Error Detection
SCRAP: Seismic collapse response prediction of steel moment resisting frames Harnessing the Potential of Pretrained Language Models and Active Learning for Tweets Sentiment Analysis
Cosmic Reionization Simulations using PINNs Forecast the diagnostic group (PTSD or CUD) from the intrusion characteristics
Testing the McGurk Effect on Multimodal Audiovisual Models CERN Compressor Vibration Analysis
Categorising Buildings in Lausanne Based on Facade Material LatentVec: Evaluating Generative Models for Vector Graphics with Interpretable latent states.
Analysis of View-out Impression Data Predicting Patent Success: A Machine Learning Approach to Commercialization Prospects
Image processing/pattern recognition on MHD spectrograms to automate the detection of phase in the discharge characterized by Magneto-HydroDynamic instabilities
Twitter sentiment analysis with ML
EEG decoding Using LLMs for Retrieval Augmented Generation on the RTS Archive
Performing 2D Nucleus Segmentation With Cellpose and StarDist on Xenium Data Deep Learning for Road Segmentation by LASMER Group
Evaluating the Performance of Ensembling Methods with CNNs for Road Segmentation Performing Sentiment Analysis on Tweets: An Analysis of Multiple Methods
Meditron-V: Empowering Meditron with Visual Understanding Identifying the neural predictors of subjective sleep quality from sleep EEG recordings in trans-diagnostic psychiatric conditions
Recurrent convolutional neural network for coronal jets identification Multi-category Multi-object Indoor Scenes Understanding for Intelligent Assistive Environment
Submission - Laurel and Hardy Radiated power reconstruction given BOLO/AXUV line integrated measurements
RoadMaster: Mastering Road Segmentation using Deep Neural Networks Predicting brain activity during movie watching: from the movie frames to the brain
Shallow-learning Movement recognition for physiotherapy
ML-powered Tool for assisted design of Buildings Machine Learning: Generalizable Yeast Cell Segmentation
ML4Science in collaboration with LAPD Investigation of the operational parameters for QCE H-mode regime access in TCV plasmas through unsupervised learning
Machine Learning for Chess Movement Recognition LSIR - Argument quality
Road Segmentation Exploring Transformer Models for Page Prefetching
Neural Control Systems (ML4S, reproduction paper) Fine-tuning Large Language Models for Argument Stance Detection in Unseen Domains
Exploration for mutants with enhanced protein fitness Road segmentation using Transfer Learning approach from pre-trained U-Net models
Crafting Metrics for MiniMeditron Reward Models Gammagrou Text-Classification
Twitter Sentiment Analysis: BERT’s emojis Estimation of Brazil Nut Productivity in the Amazon (Madre de Dios)
Coronal Mass Ejection prediction from spacecraft EDAC measures Train generalist deep neural networks with database of annotated images: MEDIAR Architecture
Enhancing Fear Detection in GBV Survivors: A Deep Learning Approach with Physiological Data Analysis Tweet sentiment classification
Identification of radiative instability patterns Road Segmentation with CBAM2U-Net
Predicting lipid abundance in a murine brain section from spatial gene expression Federated Learning with Partial Model Personalization
4
2
0
2
3
 why ML?

Applications, cont.
 Image Data

✤ Astronomy
✤ Face recognition
✤ 2D + 3D medical
imaging
✤ OCR
✤ self-driving cars

[Link] (deactivated)
 neutral positive Tom Brady wins AFC offensive player of the week for 22nd time [Link]
negative negative Watching Contraband on the PVR & it's too frigging predictable to continue wa

Text Data
negative negative @JoshNorris @Rotoworld_Draft I'd be pretty mad if the Packers took Bernard in th
neutral neutral Herald Sun: AFL stars make their UFC 152 picks: DANE Swan and Gary Ablett give
negative negative Steal by Chalmers, on the break away and is fouled by Garnett. That is his 3rd fou
neutral neutral @Holly_Gilchrist you out again on Thursday for #aNightmareOnGeorgeStreet at Ch
✤ Text Understanding & Text Generation
neutral positive Free to Watch!!! Justified: Justified follows Marshal Raylan Givens, a modern day 1
neutral neutral @_BigDaddyDouley Come SUPPORT the SHOW/MOVEMENT at Park dale High Scho
✤ Spam Detection positive positive @drewbrees I admire the relationship U have with your family. Lol iron man's a pr
neutral neutral @shuayb_ well i went maths on mon, tues + wed but cba now youu? &nopee
positive positive Lance just left, dinner with the fam was great. Managed to watch Napoleon Dynam
✤ User Content positive positive Come see the David Bowie tribute show I'm in @ King King, H'wood, Nov 4 &
positive positive Your like Jordan's on a Saturday I got to have you and I cannot wait. .
✤ Medical Text negative neutral But i wanna wear my Concords tomorrow though but i don't feel like it
positive neutral Gonna watch Grey's Anatomy all day today and tomorrow(:
✤ Machine Translation negative neutral @CoachVac heey do you know anything about UVA's fallll fest loll they invited me s
neutral neutral @DustyEf when that sun is high in that Texas sky, I'll be buckin it to county fair. A
neutral positive Up 20 points in my money league with Vernon Davis and L. Fitz still to go tomorrow
neutral positive DEEJAYING this FRIDAY in THE FIRST CHOP it's CHRIS actual SMITH with a smash
negative negative The Rick Santorum signing that was scheduled for tomorrow at the Books A Million
positive neutral @dreami9 lol yep looks like it! Was after El Clasico on Sunday. I didn't like her lol a
neutral neutral Back in Stoke on Trent for the 2nd time today!
neutral neutral First Girls Varsity Basketball Game tomorrow at 6:00 pm Then Football Senior nigh
neutral neutral #UFC lightweights @Young__Assassin VS @jamievarner set for TUF 16 Finale on th
neutral neutral @OOOOO_WEEEE slide thru sometime this weekend ill have somethin yu can sip o
negative negative @DannyB618 Sure absolutely-- I meant out of the Bachmann, Perry, Santorum, H
negative negative @RichardGordon48 re Levein discussion on Wed. Can't keep changing boss, but he
neutral neutral Today In History November 02, 1958 Elvis gave a party at his hotel before going o
neutral positive Hustle cause you got to then kick back n party everyday like its Fri
positive positive I can't sleep. Way too exited about Vancouver tomorrow! I'm like a kid at Christma
Medical: Genetic Data

ref
 Audio & Multimodal Data

✤ Hearing aids
✤ Voice Recognition

✤ Automatic Translation
✤ Lip Reading
✤ Video Analysis
 Numerical / Sensor Data
✤ Cern
✤ Astronomy/ Telescopes
✤ Fitness Trackers
✤ Weather Forecast
✤ Robotics
✤ Kinect
 Games & Simulations

✤ Immediate Feedback
✤ Chess, Go
✤ Physical World
 Internet Data: Part

Products / Words
★★
★
★
★★

Customers / Words
★★

★
>
★★
★★
★
⇡ UV
★★ ★★
★★ ★

★★

★★
★★ ★
★

Recommender systems, Ads

1
Internet Data Part / Large Language Models

Virtual assistants
2
Other Generative AI models

generation of
image, video,
audio, text
modalities
New Opportunities?

Your turn
 up next:

✤ Regression
✤ Linear Regression
✤ Classi cation
✤ … fundamental concepts of ML
fi