Pascal Janetzky - Pascal Janetzky

January's reads

Viktor Frankl, James Clear, Cal Newport, and Eric-Emmanuel Schmitt

Machine Learning

Parsing the UrbanSound8K dataset with TensorFlow

From raw audio to TFRecords to data streaming

Thoughts on

Large projects, large rewards?

Or: the intangibility of Machine Learning projects

Machine Learning

Parsing the ESC50 audio dataset with TensorFlow

From audio to TFRecord to a readily-usable dataset

Machine Learning

Setting up Apple's new M1 MacBooks for Machine Learning

With the newest iteration of its custom M1 chip, the M1 Pro and M1 Max versions, Apple has given the Machine Learning community a powerful tool. To some extent, however, this power can only be unleashed if the system is set up correctly.

Thoughts on

Getting a job to work towards a raise to buy a house to build a family to retire to die

What Game of Thrones, Henry David Thoreau, Facebook, and Finance Literature offer to our remedy

Machine Learning

Preparing the ImageNet dataset with TensorFlow

Without a doubt, the ImageNet dataset has been a critical factor in developing advanced Machine Learning algorithms. Its sheer size and a large number of classes have been challenging to handle.

Neural Networks are like human bodies

Neural Networks. They seem to be everywhere. That is not a problem if you are a seasoned practitioner; you understand what they are all about. Usually, you come up with an explanation quickly.

Machine Learning

Apple's new M1 Max and M1 Pro MacBooks

The specs are indeed intimidating: Up to 32 GPU cores and up to 16 CPU cores. Pair that with 64 GB of RAM, and you're well equipped for any workload. And, not to forget the design. Well, it seems Apple did it again.

Machine Learning

Writing TensorFlow code that scales

Most of the time, we write and debug our code locally. After we've passed any tests, we then deploy the scripts to a remote environment. If we're fortunate, we might have access to multiple GPUs.

Thoughts on

On freedom.

As the moderator introduces the speaker, I look at the audience. I see some politicians from several neighbouring countries, artists, and other known people. How did I even get here?

Many hyperparameters? Use Gin

The common approaches to handling user-specific settings include parsing command line arguments or using separate python files that store definitions. For small projects, these techniques are easy to incorporate and maintain.

ML Deep Dives

Deep Reinforcement Learning: From SARSA to DDPG and beyond

The ability to make machines learn is a fascinating achievement of the last decades. Many new business opportunities have opened up, and companies use Machine Learning on a day-to-day basis.

Machine Learning

A Template for Custom and Distributed Training

Custom training loops offer great flexibility. You can quickly add new functionality and gain deep insight into how your algorithm works under the hood. However, setting up custom algorithms over and over is tedious. The general layout often is the same; it’s only tiny parts that change.

Getting TensorFlow Developer certified

After preparing for a long time, I recently took and passed the TensorFlow Developer Certificate exam. This exam tests your proficiency in using TensorFlow for image, time-series, and text data. Beyond these domains, it also covers strategies to reduce overfitting, such as augmentations and dropout layers. Why should you get

Exploring Audio Datasets with Python

Image datasets can be explored easily. Even if we have hundreds of images, we can scroll through directories and glance at the data. This way, we can quickly notice interesting properties

Machine Learning

Tips and tricks for Neural Networks

Training neural networks is a complex procedure. Many variables work with each other, and often it’s unclear what works.

Machine Learning

Recreating a Machine Learning Master’s degree with Online Courses

The internet is full of courses and offers many learning materials. You can use these resources to replicate the curriculum of an ML Master’s degree.

Machine Learning

Natural Language Processing: From one-hot vectors to billion parameter models

Human language is ambiguous. Speaking (or writing), we convey the individual words, tone, humour, metaphors, and many more linguistic characteristics. For computers, such properties are hard to detect in the first place and even more challenging to understand in the second place.

Machine Learning

Recreating a Computer Science Bachelor Degree with online courses

Many universities make their curriculums publicly available, listing all required courses to attain a degree. The Computer Science field is no different. Using such freely accessible resources, one can create a custom schedule.

Machine Learning

Visualizing Audio Pipelines with Streamlit

When working with image data, practitioners often use augmentations. Augmentations are techniques that artificially and randomly alter the data to increase diversity. Applying such transformations to the training data makes the model more robust.

Machine Learning

A guide to the field of Deep Learning

The field of Machine Learning is huge. You can easily be overwhelmed by the amount of information out there. To not get lost, the following list helps you estimate where you are. It provides an outline of the vast Deep Learning space.

Machine Learning

Writing Machine Learning Code that scales

After you have finally created that training script it’s time to scale things up. From a local development environment, be it an IDE or Colab, to a large computer cluster, it’s quite a stretch. The following best practices make this transition easier.

Machine Learning

A checklist to track your Machine Learning progress

Have you ever asked yourself where you currently are on your Machine Learning journey? And what’s there that you can still learn about? This checklist helps you answer such questions. It provides an outline of the field, divided into three broad levels: Entry level (where everybody starts), intermediate level

ML Deep Dives

An Introduction to Reinforcement Learning

Recent successes, achieved with the help of Reinforcement Learning, have quite extensively been covered by the media. One can think of DeepMind’s AlphaGo algorithm: It learned to play the age-old game of Go and even developed its own playstyle.