Data Skeptic

Kyle Polich

4,0 (2)
TECNOLOGIA
QUINZENALMENTE

The Data Skeptic Podcast features interviews and discussion of topics related to data science, statistics, machine learning, artificial intelligence and the like, all from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.

-6 DIAS

Open Animal Tracks

Our guest today is Risa Shinoda, a PhD student at Kyoto University Agricultural Systems Engineering Lab, where she applies computer vision techniques. She talked about the OpenAnimalTracks dataset and what it was used for. The dataset helps researchers predict animal footprint. She also discussed how she built a model for predicting tracks of animals. She shared the algorithms used and the accuracy they achieved. She also discussed further improvement opportunities for the model.

23 min
10/09

Bird Distribution Modeling with Satbird

This episode features an interview with Mélisande Teng, a PhD candidate at Université de Montréal. Her research lies in the intersection of remote sensing and computer vision for biodiversity monitoring.

40 min
26/08

Ant Encounters

In this interview with author Deborah Gordon, Kyle asks questions about the mechanisms at work in an ant colony and what ants might teach us about how to build artificial intelligence. Ants are surprisingly adaptive creatures whose behavior emerges from their complex interactions. Aspects of network theory and the statistical nature of ant behavior are just some of the interesting details you'll get in this episode.

31 min
19/08

Computing Toolbox

This season it’s become clear that computing skills are vital for working in the natural sciences. In this episode, we were fortunate to speak with Madlen Wilmes, co-author of the book "Computing Skills for Biologists: A Toolbox". We discussed the book and why it’s a great resource for students and teachers. In addition to the book, Madlen shared her experience and advice on transitioning from academia to an industry career and how data analytic skills transfer to jobs that your professionals might not always consider. Join us and learn more about the book and careers using transferable skills.

39 min
14/08

Biodiversity Monitoring

In this episode, we talked shop with Hager Radi about her biodiversity monitoring work. While biodiversity modeling may sound simple, count organisms and mark their location, there is a lot more to it than that! Incomplete and biased data can make estimations hard. There are also many species with very few observations in the wild. Using machine learning and remote sensing data, scientists can build models that predict species distributions with limited data. Listen in and hear about Hager’s work tackling these challenges and the tools she has built.

32 min
8/08

Hacking the Colony

Today, Ashay Aswale and Tony Lopez shared their work on swarm robotics and what they have learned from ants. Robotic swarms must solve the same problems that eusocial insects do. What if your pheromone trail goes cold? What if you’re getting bad information from a bad-actor within the swarm? Answering these questions can help tackle serious robotic challenges. For example, a swarm of robots can lose a few members to accidents and malfunctions, but a large robot cannot. Additionally, a swarm could be host to many castes like an ant colony. Specialization with redundancy built in seems like a win-win! Tune in and hear more about this fascinating topic.

41 min
31/07

Primate Poses

During this season we have talked with researchers working to utilize machine learning for behavioral observations. In previous episodes, you have heard about the software people like Richard use, but you haven’t heard much from scientists modifying and using these tools for specific research cases. PhD student, Richard Vogg, is working with multi-camera set-ups to track lemurs and macaques solving puzzle boxes in the wild. His work is part of a larger movement to automate behavioral analyses of video data. Listen in and learn why this tech is useful and why multi-camera setups are a good idea for more reliably identifying poses and individual animals.

33 min
23/07

Generating 3D Animals with YouDream

Generative AI can struggle to create realistic animals and 2D representations often have mistakes like extra limbs and tails. If 2D wasn’t hard enough, there are researchers working on generative 3D models. 3D models present an extra challenge because there is paucity of training datasets.In this episode, PhD students Sandeep and Oindrila walked us through their work on creating 3D animals using 2D data. Join us to learn about their pipelines, quality control, tie in with iNaturalist, and how this tech could streamline FX pipelines.

1 h 0 min

Ver tudo (546)

Kyle Polich

Apresentador(a)

4

de 5

2 classificações

The Data Skeptic Podcast features interviews and discussion of topics related to data science, statistics, machine learning, artificial intelligence and the like, all from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.

Autoria

Kyle Polich
Anos em atividade

2014 - 2024
Episódios

546
Classificação

Para todos
Site do programa

Data Skeptic

Data Skeptic

Open Animal Tracks

Bird Distribution Modeling with Satbird

Ant Encounters

Computing Toolbox

Biodiversity Monitoring

Hacking the Colony

Primate Poses

Generating 3D Animals with YouDream

Apresentadores e convidados

Kyle Polich

Classificações e críticas

Sobre

Informação

Talvez também goste

Data Skeptic

Episódios

Open Animal Tracks

Bird Distribution Modeling with Satbird

Ant Encounters

Computing Toolbox

Biodiversity Monitoring

Hacking the Colony

Primate Poses

Generating 3D Animals with YouDream

Apresentadores e convidados

Kyle Polich

Classificações e críticas

Sobre

Informação

Talvez também goste