Podcast Episodes

Back to Search
Protecting workers with artificial intelligence (with Sandeep Pandya CEO Everguard.ai)(Ep. 106)

Episode 103

In this episode I have a chat with Sandeep Pandya, CEO at Everguard.ai a company that uses sensor fusion, computer vision and more to provide safer w…

5 years, 10 months ago

Short Long
View Episode
Compressing deep learning models: rewinding (Ep.105)

Episode 102

As a continuation of the previous episode in this one I cover the topic about compressing deep learning models and explain another simple yet fantast…

5 years, 11 months ago

Short Long
View Episode
Compressing deep learning models: distillation (Ep.104)

Episode 101

Using large deep learning models on limited hardware or edge devices is definitely prohibitive. There are methods to compress large models by orders …

5 years, 11 months ago

Short Long
View Episode
Pandemics and the risks of collecting data (Ep. 103)

Episode 100

Codiv-19 is an emergency. True. Let's just not prepare for another emergency about privacy violation when this one is over.

 

Join our new Slack chan…

5 years, 11 months ago

Short Long
View Episode
Why average can get your predictions very wrong (ep. 102)

Episode 99

Whenever people reason about probability of events, they have the tendency to consider average values between two extremes. 
In this episode I explai…

6 years ago

Short Long
View Episode
Activate deep learning neurons faster with Dynamic RELU (ep. 101)

Episode 98

In this episode I briefly explain the concept behind activation functions in deep learning. One of the most widely used activation function is the re…

6 years, 1 month ago

Short Long
View Episode
WARNING!! Neural networks can memorize secrets (ep. 100)

Episode 97

One of the best features of neural networks and machine learning models is to memorize patterns from training data and apply those to unseen observat…

6 years, 1 month ago

Short Long
View Episode
Attacks to machine learning model: inferring ownership of training data (Ep. 99)

Episode 96

In this episode I explain a very effective technique that allows one to infer the membership of any record at hand to the (private) training dataset …

6 years, 1 month ago

Short Long
View Episode
Don't be naive with data anonymization (Ep. 98)

Episode 95

Masking, obfuscating, stripping, shuffling. 
All the above techniques try to do one simple thing: keeping the data private while sharing it with thir…

6 years, 1 month ago

Short Long
View Episode
Why sharing real data is dangerous (Ep. 97)
Why sharing real data is dangerous (Ep. 97)

Episode 94

There are very good reasons why a financial institution should never share their data. Actually, they should never even move their data. Ever.
In thi…

6 years, 2 months ago

Short Long
View Episode

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us