# ML-DL > Machine Learning Blog ## Posts - [But What Are Word Embeddings?](https://ml-dl.com/but-what-are-word-embeddings/): Simple. Neural Networks only understand numerical data. Their weights, their biases, and their training, all take place using numerical values, floats, and integers, yada yada. Now when we want to work with words and other textual data, we need a way to convert them to numerical representation, that’s where word embeddings come under the picture. Natural Language Processing What is Natural Language Processing? It’s a vast field of science, that comes under the category of linguistics, it has been there even before the recent developments in machine learning and deep learning came into the picture. It comprises techniques like Stemming […] - [What is Federated Learning](https://ml-dl.com/what-is-federated-learning/): With the concerns about data privacy rising and with the rise of AI models, people are increasingly concerned about their data being misused for purposes beyond their consent. As we know that data is the new oil of this century, it is a very sought after commodity. Seeing these concerns, Google introduced the concept of federated learning back in 2016. Let’s delve into this topic a bit and understand what it is. Understanding Federated Learning Federated Learning is like a team of learners working together without revealing their individual knowledge. I am not sure what analogies you can put forward […] - [Generative Adversarial Networks (GANs) From Scratch](https://ml-dl.com/generative-adversarial-networks-gans-from-scratch/): Generative Adversarial Networks (GANs) are incredibly powerful in the world of machine learning. They excel at creating synthetic data that’s so close to real data, it’s almost uncanny. Today, we’re diving into how these networks work and even trying our hand at building a simple GAN framework using PyTorch. But why the term “Adversarial”? Well, it’s because GANs work on a fascinating dynamic between two networks: the Generator and the Discriminator. The Generator takes in random noise and tries to generate an output. At first, this output might seem like random noise, but the magic happens as it gets refined […] - [Universal Backdoor Attacks](https://ml-dl.com/universal-backdoor-attacks/): Today I will be discussing my understanding of the paper Universal Backdoor Attacks. The paper delves into another exciting exploit that can be leveraged against popular convolutional models such as Resnets. What is a Universal Backdoor A backdoor is an alternate entry to your house. In the field of computers and security in general, it means an illicit way of accessing a system( or model in this context). The paper discusses how a backdoor can be universal, i.e. serve its purpose for multiple scenarios, as we will see further. Model Poisoning Model poisoning is when you corrupt the data of […] - [Remember What You Want To Forget](https://ml-dl.com/remember-what-you-want-to-forget/): So today I will be analyzing and providing a brief summary of my understanding of this paper titled Remember What You Want To Forget This paper presents one of the algorithms for machine unlearning. Machine Unlearning is an important practice when it comes to privacy and security in machine learning. Machine unlearning algorithms aim to make the model forget certain data points that they were trained upon, with the added complexity of retaining the performance as before. This can have a wide range of applications, especially in the current times when ML models are almost everywhere, and learning from our […] - [What is Differential Privacy?](https://ml-dl.com/what-is-differential-privacy/): Differential privacy is a technique devised for data analysis whilst maintaining the privacy of the individuals whose data is involved. It was first introduced in the year 2006, by Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith and has been one of the foundational pillars in the intersection of data science and privacy. At its core, differential privacy mathematically ensures that the presence or absence of any individual’s data in a dataset will not significantly affect the outcome of any analysis or query. The Differential Privacy Mechanism Differential privacy involves adding random noise to the dataset. To achieve this, […] - [BIM: Advanced FSGM Attack](https://ml-dl.com/bim-advanced-fsgm-attack/): Previously we talked about Fast Sign Gradient Method( FGSM), we saw how this white box technique, cleverly exploits the gradients in a model, to perturb the input to give the wrong prediction from the model. Since, in this method, we perturb our input just once, a modified version of this attack does so repeatedly for a given number of iterations. Earlier in FSGM, we compute the gradient of the loss computed by feeding the input into the model, with respect to the input, and then update the input in the same direction as the gradient so as to maximize loss. […] - [Gradient Descent](https://ml-dl.com/gradient-descent/): The special ingredient to machine learning. We learned in the last post about Linear Regression. We concluded with a cost function that we needed to minimize. Today we will see how we minimize this cost function. To recap, the cost function was : Here, h𝚯(x) is the linear regression equation that we discussed earlier( y= mx+c). here m is represented as theta. One can write the equation as For multivariate linear regression, it would then become and the corresponding hypothesis function would be then The c is often called so we write the above equation as : Where x0 is […] - [Adversarial Attacks](https://ml-dl.com/adversarial-attacks/): In this post, we will be talking about the vulnerabilities that plague machine learning. Yes, in the realm of computer science, no field is void of vulnerabilities and loopholes and as we progress towards a very AI-based future, the security and robustness of machine learning models become an important aspect. What are Adversarial Attacks? The term “adversarial” means opposing or conflicting in nature. So intuitively, it could mean an attack based on conflicting behavior or outcome. Well, that’s what an adversarial attack is. Traditional machine learning models are trained to minimize a loss function and optimize for accurate predictions, during […] - [Linear Regression in Python: The Naive Way](https://ml-dl.com/implementing-linear-regression-in-python-the-naive-way/): A short guide on how to implement linear regression using libraries. Hola mates, long time no C. Yeah, I am just a Python guy and I don’t like C/C++ too much simply because they aren’t that handy. A programming language is a tool that should be easy to use and should allow you to implement and do stuff and not waste your time configuring and reading the manuals. So today we will see how to implement linear regression in Python. If you went through my older posts you know it’s something the stats guys use all the time. A linear […] - [Linear Regression](https://ml-dl.com/linear-regression/): Let’s look at the hello world of machine learning algorithms. In this post, we will look at a very simple machine learning algorithm which is actually the “hello world” equivalent of programming languages. So what is linear regression? If you are from a statistics background chances are you already know what it means. In statistics, linear regression is a tool that is used for finding a relation between a dependent variable and an independent variable. It’s that simple. Consider the equation below. This is a linear equation that captures the relationship between the variables y and x. The variable y […] - [Can You Hide Malware in Neural Networks?](https://ml-dl.com/can-you-hide-malware-in-neural-networks/): Let us start with something simple. We download a neural network to try out in a project. It might sort images or help with a data pipeline. That model looks like just a file we use and forget. Now imagine that file is carrying a hidden payload. It might sound like a thought experiment, but researchers have shown ways to embed data inside model parameters. That work is often called MaleficNet in the research literature. We will walk through what that means, why it is surprising, and what it implies for anyone who uses or shares models. We will keep […] - [Label Flipping Attacks in Federated Learning: The FedTrident Defense Explained](https://ml-dl.com/label-flipping-attacks-in-federated-learning-the-fedtrident-defense-explained/): Autonomous vehicles need to classify road conditions in real time. Wet roads, icy surfaces, severe potholes. The model needs to know so the vehicle can adjust speed, traction, suspension before it gets there. Training that model needs data. Lots of it. From lots of different roads, weather conditions, geographies. You could collect it all centrally, but then every vehicle is uploading raw camera footage to a server somewhere. Privacy problem. Bandwidth problem. Increasingly a legal problem. GDPR, CCPA, PIPL all push back against bulk data aggregation. The differential privacy post covers that regulatory picture if you want to go deeper. […] - [Understanding Recurrent Neural Networks (RNNs)](https://ml-dl.com/understanding-recurrent-neural-networks-rnns/): With so much noise out there with LLMs and GPTs, we often tend to forget the basic building blocks or the primitive concepts that led to the advancement of these technologies. Recurrent Neural Networks, or RNNs in short are one of the basic concepts that lead to a better understanding of these advanced concepts. In this article, we will cover the basic concept and idea behind RNNs, how they work, and their applications. Before we can begin, you must understand the basics of Neural Networks, if not, then check it out ASAP. Sequential Data: Where RNNs find their use. When […] - [Machine(Human) Learning in Daily Life](https://ml-dl.com/machinehuman-learning-in-daily-life/): The Basic Premise Think about it. What is the basic premise on which Machine Learning works? Learning to update its weights, which updates its “beliefs” about something, based on how often it makes a “mistake.” We apply for jobs, click apply, get rejected, if lucky, you get feedback : why not me? However, most companies avoid it, because they know you’re going to update your belief of what works for that company, and reapply, or help others do the same. You try sticking to a fitness program, satisfying the constraint of results + consistency, and based on that you find […] ## Pages - [Blog](https://ml-dl.com/blog/): BLOG Explore all the interesting topics, the latest exciting research in deep learning, and so on. . - [Subscribe](https://ml-dl.com/subscribe/) - [Home Page](https://ml-dl.com/) [comment]: # (Generated by Hostinger Tools Plugin)