In the last week, we took a plunge into the core concepts of Deep Learning and the framework of a Neural Network. We also touched upon the basics of an objective function and its use, the kinds of objective functions and how Gradient Descent plays a pivotal role in rectifying the mistakes/error while predicting a value.In this article, we shall feast our mind and thought on … [Read more...] about Deep Learning — Week 3, Part 2
Artificial Intelligence
Deep Learning — Week 4
Consider the task of simple Image Classification (recognising the contents of an image and assigning a certain label to them: for example, a picture of the Taj Mahal can be classified/ assigned the label of “monument”.)In the earlier examples of applying kernels to images and performing convolutions, we observed that we used hand-crafted kernels such as edge detectors and … [Read more...] about Deep Learning — Week 4
Can AI Be Governed?
PreambleThe artificial intelligence revolution will potentially change the composition of all human society and might even transform humanity itself. The transnational, boundary-bridging character of AI calls for a multistakeholder platform of global governance. Based on a shared proposal of the governments of France and Canada, the Intergovernmental Panel on Artificial … [Read more...] about Can AI Be Governed?
Speech to Text with Wav2Vec 2.0
Wav2Vec2 is a speech model that accepts a float array corresponding to the raw waveform of the speech signal. Wav2Vec2 model was trained using connectionist temporal classification (CTC) so the model output has to be decoded using Wav2Vec2Tokenizer (Ref: Hugging Face)I have used Liam Neeson famous dialogue audio clip from the movie “Taken” in this example which says “I will … [Read more...] about Speech to Text with Wav2Vec 2.0
What’s Next If You Can’t Get a Data Scientist Job
Not all data scientist jobs are equalPositions with data scientist titles may not require building machine learning models to be the main responsibility. Look for data scientist jobs that are mostly data analyst responsibilities such as evaluating A/B tests and building dashboards with some modeling required. Since machine learning is just one responsibility, the technical … [Read more...] about What’s Next If You Can’t Get a Data Scientist Job
This lighter backpack can generate electricity to power small electronics
Image Credit: Credit: Adapted from ACS Nano 2021, DOI: 10.1021/acsnano.0c07498FUTURE TECHThe proof of concept design not only lightens the load but also uses human motion to generate electricityI still remember the good old early school days, when we used to carry a heavy backpack with lots of books in it. Carrying such a load was perhaps the most uncomfortable part of going to … [Read more...] about This lighter backpack can generate electricity to power small electronics
Artificial Intelligence: Week #6 | 2021
This week in AI & Machine Learning: Teaching dogs with ML, Azure in space, TensorFlow 3D, building object detection datasets, Swift for TensorFlow shuts down, and moreSixgill Tip of the Week: Save time labeling complex objects by using the track forward and smart polygon selection features in Sense Data Annotation. Label objects in one frame and they will be automatically … [Read more...] about Artificial Intelligence: Week #6 | 2021
Detailed Explanation of Simple Linear Regression, Assessment and, Inference with ANOVA
Step by Step Discussion and Workout with Examples, Implementation manually and in RA linear relationship between two variables is very common. So, a lot of mathematical and statistical models have been developed to use this phenomenon and extract more information about the data. This article will explain the very popular methods in statistics Simple Linear Regression (SLR).This … [Read more...] about Detailed Explanation of Simple Linear Regression, Assessment and, Inference with ANOVA
NER, Métodos supervisados II: máquina de soporte vectorial y campos aleatorios condicionales
En, el artículo anterior (NER, Métodos supervisados I: cadenas de Markov y máxima entropía) se abarcaron los métodos de máxima entropía y cadenas ocultas de Markov, se explicó el mecanismo de funcionamiento de ambos métodos así como ejemplos de utilización. Como continuación, el presente artículo se va a enfocar en los modelos de máquina de soporte vectorial (SVM) y campos … [Read more...] about NER, Métodos supervisados II: máquina de soporte vectorial y campos aleatorios condicionales
Feature Selection With Practical Approach
The very first features that we should remove from our dataset are constant ones. It might seem easy to perform manually but suppose you have 200–300 features. In that case, using some technique make sense.Firstly, let import all the required libraries. Pandas is used to create and manipulate the dataset. VarianceThreshold is used to remove the features that have low variance. … [Read more...] about Feature Selection With Practical Approach