Be it Andrew Ng's ML/DL course on YouTube or any Data Science Bootcamp, you will need a certain degree of mathematical and statistical knowledge to not only understand but make a long-lasting, robust career as a data professional. This is a short and precise guide for all autodidact and beginners in the field of Data Science and Machine Learning. A common question that pops out from all my training programs, LinkedIn courses, videos on YT, or newsletters is that when they start learning DS/ML, after a certain point, they feel lost in mathematics or statistics and sometimes programming. And I have always recommended learning or refreshing some mathematical concepts that underpin ML as it helps you build intuition which keeps you curious throughout your learning journey.

"Robots will be able to do everything better than us…I am not sure exactly what to do about this. This is really the scariest problem to me." Elon musk SXSW 2018 As we saw in the previous article what is Artificial Intelligence – Explained! Basically, AI is Artificial intelligence (AI), the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. The term "human error" was born when people make mistakes from time to time. Computers, however, do not make these errors if they are correctly programmed. With Artificial Intelligence, decisions are made based on previously obtained knowledge using a series of algorithms.

The pandemic actually gave us a whole new perspective on online learning. With the online meets replacing actual classes, both the students and the teachers now understand the working of the online classes very well. But now, with the pandemic on decline, we should not neglect the online mode of learning, instead nurture it with the use of AI.

Machine learning is broadly divided into supervised, unsupervised, semi-supervised, and reinforcement learning problems. Machine learning has enjoyed the majority of success by tackling supervised learning problems...

We establish a broad methodological foundation for mixed-integer optimization with learned constraints. We propose an end-to-end pipeline for data-driven decision making in which constraints and objectives are directly learned from data using machine learning, and the trained models are embedded in an optimization formulation. We exploit the mixed-integer optimization-representability of many machine learning methods, including linear models, decision trees, ensembles, and multi-layer perceptrons. The consideration of multiple methods allows us to capture various underlying relationships between decisions, contextual variables, and outcomes. We also characterize a decision trust region using the convex hull of the observations, to ensure credible recommendations and avoid extrapolation. We efficiently incorporate this representation using column generation and clustering. In combination with domain-driven constraints and objective terms, the embedded models and trust region define a mixed-integer optimization problem for prescription generation. We implement this framework as a Python package (OptiCL) for practitioners. We demonstrate the method in both chemotherapy optimization and World Food Programme planning. The case studies illustrate the benefit of the framework in generating high-quality prescriptions, the value added by the trust region, the incorporation of multiple machine learning methods, and the inclusion of multiple learned constraints.

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and composing lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple approach that produces such a representation by using the value functions corresponding to each lower-level skill. These value functions capture the affordances of the scene, thus forming a representation that compactly abstracts task relevant information and robustly ignores distractors. Empirical evaluations for maze-solving and robotic manipulation tasks demonstrate that our approach improves long-horizon performance and enables better zero-shot generalization than alternative model-free and model-based methods.

We introduce Language-Informed Latent Actions (LILA), a framework for learning natural language interfaces in the context of human-robot collaboration. LILA falls under the shared autonomy paradigm: in addition to providing discrete language inputs, humans are given a low-dimensional controller $-$ e.g., a 2 degree-of-freedom (DoF) joystick that can move left/right and up/down $-$ for operating the robot. LILA learns to use language to modulate this controller, providing users with a language-informed control space: given an instruction like "place the cereal bowl on the tray," LILA may learn a 2-DoF space where one dimension controls the distance from the robot's end-effector to the bowl, and the other dimension controls the robot's end-effector pose relative to the grasp point on the bowl. We evaluate LILA with real-world user studies, where users can provide a language instruction while operating a 7-DoF Franka Emika Panda Arm to complete a series of complex manipulation tasks. We show that LILA models are not only more sample efficient and performant than imitation learning and end-effector control baselines, but that they are also qualitatively preferred by users.

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a teacher's preferences without pre-defined rewards, thus overcoming concerns associated with reward engineering. However, it is difficult to quantify the progress in preference-based RL due to the lack of a commonly adopted benchmark. In this paper, we introduce B-Pref: a benchmark specially designed for preference-based RL. A key challenge with such a benchmark is providing the ability to evaluate candidate algorithms quickly, which makes relying on real human input for evaluation prohibitive. At the same time, simulating human input as giving perfect preferences for the ground truth reward function is unrealistic. B-Pref alleviates this by simulating teachers with a wide array of irrationalities, and proposes metrics not solely for performance but also for robustness to these potential irrationalities. We showcase the utility of B-Pref by using it to analyze algorithmic design choices, such as selecting informative queries, for state-of-the-art preference-based RL algorithms. We hope that B-Pref can serve as a common starting point to study preference-based RL more systematically. Source code is available at https://github.com/rll-research/B-Pref.

If you were asked to say what technologies you think have had the biggest impact on shaping our world, what would your answers be? Some examples that would likely feature might include electricity, the telephone, the computer and so on. Last time I asked students this question the most common response was wifi. Back in 1995 if you wanted to surf/work/learn on the internet you'd need to be tethered to a network cable (I still see some organisations working like this today). To anyone under the age of 45 wifi is generally given the same status as any wider utility, with the speed of broadband connectivity now forming a major part of the buying decision when people look at new homes.

This is technically Deep Learning in Python part 11 of my deep learning series, and my 3rd reinforcement learning course. Deep Reinforcement Learning is actually the combination of 2 topics: Reinforcement Learning and Deep Learning (Neural Networks). While both of these have been around for quite some time, it's only been recently that Deep Learning has really taken off, and along with it, Reinforcement Learning. The maturation of deep learning has propelled advances in reinforcement learning, which has been around since the 1980s, although some aspects of it, such as the Bellman equation, have been for much longer. Recently, these advances have allowed us to showcase just how powerful reinforcement learning can be.