149. Data Scientists and Machine-Learning Engineer
These 2 engineering jobs sounds pretty close, but are involved in different phases in AI development.
Category AI
148. Similar Losses in Pytorch
I found these losses quite hard to distinguish between each other. So, I created an intuitive explanation of the differences.
147. Why Squared Loss?
Why do we use squared loss instead of absolute loss? One reason is because by squaring the loss you can magnify it which can help train the model. Another reason is because absolute loss is not differentiable when equals 0.…
146. BERT
What is BERT? BERT is a deep learning architecture for natural language processing. If you stack the Transformer’s encoder, you get BERT. What can BERT Solve? Neural Machine Translation Question Answering Sentiment Analysis Text Summarization How to solve the problems…
145. Multi-Class vs Multi-Label / SoftMax vs Sigmoid
Multi-Class = 1 class per image Multi-Label = Includes multiple label in a single image Softmax = Scale output to 0~1 and make the sum equal to 1 so that it becomes probabilities. Useful for multi-class classification. Sigmoid = Scale…
144. Visualizing 3D Volume Data
You can use 3DSlicer to visualize 3d medical data. Note that you need to convert your data to a volume(nifti file) if your current data is a single section(such as dcm file).
143. Discriminative and Generative Models
Discriminative models predict using conditional probability which makes them more robust to outliers. On the other hand, generative models tries to learn the distribution. This can be useful when you want to generate new data.
141. Caching Dataset For Faster Training
The time for training a computer vision model can be quite long which leads to a slower PDCA cycle. One way for speeding up training is caching the dataset before starting the training. When you load your data to the…
140. Spatial Pyramid Pooling
Spatial Pyramid Pooling helps the network output the same shape regardless of any aspect ratio and input size. Instead of Pooling with a fixed filter size, it divides the input with different levels of ratio, so the output would not…
139. Tools For Research
Here are some tools I use when doing research on academic papers. Arxiv-Sanity: This gives a preview of the research paper without the need of downloading the pdf. PaperWithCode:This site offers a link to code implementaion as well ConnectedPapers: This…